Research Blog

In today’s ever-evolving landscape of manufacturing, the call for sustainable practices has risen beyond a mere catchphrase, transforming into an urgent mandate for industries across the globe. As the world grapples with mounting apprehensions regarding the depletion of natural resources and environmental decline, the imperative to reevaluate and revolutionize conventional manufacturing methodologies looms larger than ever before (Hamia et al., 2015).

Sustainability in manufacturing signifies an evolution from the conventional paradigms of production. It encompasses a comprehensive approach aimed at minimizing environmental impact, optimizing resource utilization, and fostering economic resilience. As consumers demand eco-friendly products and regulatory frameworks become more stringent, manufacturers are compelled to reassess their practices to align with sustainability objectives. This entails more than mere token gestures, it necessitates a fundamental shift in how products are conceptualized, designed, produced, and disposed of.

Understanding Sustainable Manufacturing

Sustainable manufacturing represents a significant departure from conventional production paradigms, encompassing dimensions beyond mere profit considerations to include environmental and societal well-being (Hamia et al., 2015). At its essence, sustainable manufacturing seeks to achieve a delicate equilibrium between economic prosperity, environmental preservation, and societal advancement. This involves not only curtailing resource depletion, pollution, and waste generation but also fostering innovation, economic growth, and the overall welfare of communities. Achieving these goals necessitates optimizing material utilization, minimizing energy consumption, and embracing cleaner and more sustainable production processes.

In an era marked by rapid transformation, the integration of artificial intelligence (AI) into manufacturing offers promising potential to pave the way toward a more sustainable future. By comprehending the transformative influence of AI on various facets of manufacturing operations, we lay the foundation for discussions that transcend the realms of technological adoption alone.

Role of Artificial Intelligence in Manufacturing

Artificial Intelligence (AI) has emerged as a transformative force in various industries, and manufacturing is no exception. It is a multidisciplinary field encompassing machine learning, robotics, and data analysis, and has demonstrated its prowess in processing vast amounts of data and deriving actionable insights. This capacity for real-time analysis and optimization renders AI an invaluable tool in the context of manufacturing, poised to reshape the industry on a fundamental level.

In modern manufacturing, the demand for meeting throughput, quality, and cost objectives while ensuring sustainability presents challenges. AI offers unique capabilities, especially in problem-solving, by identifying intricate patterns within vast datasets generated by machines, sensors, and controllers. These data categories range from environmental data to production operation records, creating opportunities for pattern discovery. This capability enhances root cause analysis and offers insights into system behavior, aligning with the hierarchical approach to manufacturing systems (Arinez et al., 2020).

However, the impact extends beyond operations, addressing long-standing industry challenges. Balancing cost-effective production with environmental sustainability is a prime concern. AI’s predictive prowess optimizes processes while minimizing resource waste, aligning with eco-friendly practices. This convergence of efficiency and sustainability aligns with the call for greener manufacturing.

Moreover, AI’s insights transcend the product lifecycle, from raw material sourcing to disposal. By identifying recycling, repurposing, and reusing opportunities, AI fosters a circular economy within manufacturing, minimizing waste and supporting sustainable production.

As manufacturing navigates a future of resource scarcity and environmental accountability, AI illuminates the path forward. Beyond profitability, AI empowers manufacturers to become stewards of sustainability, transcending traditional roles and prompting a fundamental industry transformation. This evolution is guided by AI’s ability to understand complex data patterns, adapt processes, and provide informed decision-making, securing its place as a catalyst for lasting change.

Enhancing Sustainability Through AI-Driven Applications

While machine learning has demonstrated its potential to enhance manufacturing processes, it’s essential to acknowledge that it might not be universally applicable to all manufacturing contexts. ML shines in analyzing complex processes with interrelated parameters and offering predictive insights, yet there are instances where simpler non-ML methods remain effective and practical. The decision between the two approaches hinges on factors such as the need for additional insights and the availability of expertise.

Interestingly, despite the growing role of AI in manufacturing, there exists a noticeable gap in the literature concerning its specific contributions to sustainability enhancement. While AI applications have shown promise in multiple domains, the discussion about how AI can comprehensively contribute to sustainability within manufacturing is still relatively limited. This gap calls for further exploration and research to uncover AI’s full potential in advancing sustainable manufacturing practices.

In the pursuit of harnessing the full potential of AI in manufacturing, it’s crucial to delve into the specific avenues through which AI-driven applications can bolster sustainability. These applications present opportunities to not only enhance operational efficiency but also to make substantial strides toward minimizing the environmental footprint of manufacturing processes. By incorporating AI’s analytical capabilities, manufacturers can unlock new dimensions of sustainability, optimize resource usage, reduce waste, and advance eco-friendly practices.

The integration of AI into manufacturing processes opens a realm of possibilities, each contributing to the overarching goal of sustainability. There are several applications of AI that can increase sustainability, such as process parameters optimization, predictive maintenance, efficient logistics management, predictive quality assurance, and intelligent scheduling to create a harmonious ecosystem of efficiency and environmental responsibility (Ekwaro-Osire et al., 2022). Let’s explore these key domains where AI’s influence is transforming the landscape of sustainable manufacturing.

• Process Parameters Optimization: AI brings a level of precision to manufacturing that was previously unattainable. By analyzing real-time data and identifying intricate patterns, AI optimizes process parameters. This minimizes resource waste, enhances product quality, and reduces energy consumption. Manufacturers can achieve more with less, aligning with the principles of sustainable manufacturing.

• Predictive Maintenance: Unplanned downtime due to equipment breakdowns contributes to inefficiency and environmental strain. AI’s predictive maintenance capabilities pre-emptively identify potential issues. By detecting subtle changes in equipment behavior, AI-driven systems enable timely interventions, extending equipment lifespans, and minimizing waste through resourceful maintenance.

• In- and Outbound Logistics: Efficient logistics is a cornerstone of sustainable manufacturing. AI optimizes inbound and outbound logistics, ensuring that resources and products are transported with precision timing. This not only reduces transportation emissions but also aligns with lean production principles, minimizing excess inventory and waste.

• Predictive Quality Assurance: AI’s predictive capabilities extend beyond maintenance to quality assurance. By analyzing historical and real-time data, AI can predict product defects before they occur. Manufacturers can pre-emptively address quality issues, reducing waste from subpar products and enhancing overall product excellence.

• Smart Scheduling: Intelligent scheduling is an integral part of sustainable manufacturing. AI analyses a multitude of variables to create optimal production schedules. This minimizes idle time, reduces energy consumption, and streamlines resource utilization, ensuring that every aspect of production contributes to sustainability goals.

These applications exemplify how AI acts as a catalyst for sustainability in manufacturing. By seamlessly integrating AI into these core aspects, we unlock a powerful arsenal of tools that not only optimize operations but also minimize resource waste and environmental impact. Process parameters optimization ensures that every action aligns with energy efficiency, resulting in a production process that maximizes output while minimizing input. Predictive maintenance, powered by AI’s ability to anticipate machinery needs, leads to proactive interventions, reducing unplanned downtime and the accompanying energy wastage.

Efficient logistics management, guided by AI’s real-time analysis, transforms the movement of resources and goods into a well-orchestrated symphony. This not only cuts down transportation emissions but also streamlines supply chains, minimizing excess inventory and waste. Quality assurance, backed by predictive insights, safeguards against defects, reducing the need for rework and curbing material waste. In the realm of intelligent scheduling, AI’s intricate algorithms pave the way for resource-efficient production timelines, where energy-intensive processes align seamlessly with peak demand.

Conclusion

The fusion of Artificial Intelligence (AI) and sustainable manufacturing has illuminated a path toward a future where efficiency, innovation, and environmental stewardship converge. In this analysis, we’ve journeyed through the symbiotic relationship between AI and manufacturing processes, uncovering how AI serves as a driving force for sustainability across various dimensions.

The transformative potential of AI in manufacturing is undeniable. From optimizing process parameters and predictive maintenance to efficient logistics management and intelligent scheduling, AI applications amplify efficiency while minimizing resource waste and environmental impact. The intricate dance between AI and sustainable manufacturing offers manufacturers the ability to balance economic growth with responsible resource utilization.

AI-driven sustainable manufacturing transcends theoretical musings, as real-world implementations continue to yield impressive results. Companies leveraging AI to optimize processes, reduce downtime, and enhance logistics efficiency have seen quantifiable improvements in their environmental footprint and operational profitability. As these success stories accumulate, they inspire a broader shift toward a manufacturing landscape that not only meets present demands but also safeguards the planet for future generations.

References

Ekwaro-Osire, H., Bode, D., Thoben, K.-D., & Ohlendorf, J.-H. (2022). Identification of Machine Learning Relevant Energy and Resource Manufacturing Efficiency Levers. Sustainability, 14(23), 15618. https://doi.org/10.3390/su142315618

Hamia, N., Muhamad, M. R., & Ebrahim, Z. (2015). The Impact of Sustainable Manufacturing Practices and Innovation Performance on Economic Sustainability. Procedia CIRP, 26, 190-195.

Arinez, J. F., Chang, Q., Gao, R. X., Xu, C., & Zhang, J. (2020). Artificial Intelligence in Advanced Manufacturing: Current Status and Future Outlook. Journal of Manufacturing Science and Engineering, 142, 110804.

1. Quality Inspection for Excellence in Manufacturing

Quality inspection and, more specifically, production with zero defects have been explored in recent years, both from academia and industry. Even the increase in the quality of European products is aligned with Europe’s desire to create a European industry focused on delivering high-quality products and sustainability by reducing waste, improving the consumer experience, and developing economically viable businesses [1]. Hence, companies must use new technologies to implement this in their production environments. Recent developments in Information and Communication Technologies and Computer Science have explored approaches based on machine learning models to improve the production process for the most varied purposes [2]. Regarding quality inspection, it is possible to verify that several studies have been proposed in various industrial sectors, such as semiconductors [3], wheel-rim molding [4], or even injection molding [5]. However, these approaches usually require highly specialized labor for designing the machine learning models and preparing an integrated solution in the factory. Moreover, with the new developments aligned with Industry 5.0[6], aligning these approaches with the needs and requirements also defined by the human (operators, engineers, product designers, etc.) is imperative.

Currently, most of the solutions presented for quality inspection that uses Artificial Intelligence (AI) classify products as OK or NOK or identify the type of defect the product has, doing it autonomously and without human intervention. It is still possible to find approaches in which the system tries to predict possible defects before they occur, considering the process parameters and their evaluation over time.

2. Artificial Intelligence for Predictive Quality

There are several approaches to detecting defects in production. However, traditional methods tend to analyze the product and the process from the standpoint of detecting defects as soon as they occur rather than trying to predict and prevent them from occurring. With the emergence of AI, it was possible to start predicting system behavior by considering historical process information, as with production defect detection. In the case of industrial processes, it is possible to use AI to predict the emergence of production defects by monitoring the parameters that can be extracted from the process (velocities, temperatures, forces, etc.). In this way, by making AI models capable of perceiving whether different combinations of parameters may result in production defects, it is possible to alert and stop production before it occurs under these conditions, thus moving to quality prediction.

To implement this approach, it is necessary to perform some steps before creating the machine learning model and deploying it to be used in production.

2.1.    Data Collection

This phase aims to ensure that methodologies and solutions are developed to extract the necessary data from the process and the product. In other words, this first phase focuses on integrating software and the different machines to send the execution data to an environment where this data can be stored and later analyzed. In this phase, it is necessary to see which communication protocols will be used to extract the data, such as OPC-UA [7], which has been gaining increasing traction in the industrial environment, facilitating data extraction.

In addition to data extraction, it is also necessary to ensure that this data is pre-processed and stored to be used later to create machine learning models. So, we move on to the next phase, which is pre-processing.

2.2. Pre-Processing

The data that appears in the raw format must be processed in such a way that this data can be useful for generating the knowledge and models we want. So, there is some pre-processing required to transform this unorganized data into something that can be useful. This process depends mainly on the machines we monitor and how they make the data available. We have cases where the data is already generated but is stored in files like text or CSV. In other cases, we have data generated continuously, which needs to be jobs stored in various entries that may make sense. Not only does the data need to be extracted, but it also needs to be harmonized and saved according to a known data model so that it can be recognized when used. This whole process of transforming raw data into data organized and saved in a known format is called pre-processing. After this process phase, we can move on to the steps closer to creating machine learning models.

An example of a dataset after pre-processing could be the following, shown in Table 1.

Machine 1
Parameter 1	Parameter 2	Parameter 3	Parameter 4
2345	432	352	325
546	213	345	543
654	2143	324	453

2.3. Labeling

In the case of quality inspection, the objective in most cases is the creation of a classifier that will indicate whether the product will be defective or not when the process has a specific combination of parameters. To create these classifiers, it is then necessary to do the labeling of the data we have at our disposal (historical data). So, simplistically, the labeling process focuses on identifying, for each of the saved parameter combinations, the execution as OK or NOK (Not OK). The goal is to add more data to the dataset indicating whether the products were produced correctly or with defects for each run. It is also possible to make some variations to the labeling. For example, instead of just classifying as OK or NOK, classifying with different types or severity of defects. In this case, it would be something like OK, defect type 1, defect type 2, etc.

Using the example in Table 1, the dataset after labeling could look like this (Table 2). In the end, the goal is for our machine learning model to be able to predict the result of the last column, given as input the parameters (Parameter 1 to 4).

Machine 1
Parameter 1	Parameter 2	Parameter 3	Parameter 4	OK/NOK
2345	432	352	325	OK
546	213	345	543	NOK
654	2143	324	453	OK

There are several approaches to labeling, the most traditional and usually the manual labeling, which a person either done later by a developer or engineer or even by an operator during production, using additional software, such as a Smart MES, which allows the operator to enter whether a product has a defect or not. In addition to the more traditional approach, it is possible to use automatic or semi-automatic techniques.

2.4. Model Creation

After the previous steps, we can create our predictive models using machine learning algorithms. For the creation of the models, data is used to train the models, and data is used to test whether the models created have acceptable performance in the classifications. Thus, the dataset is divided into a training dataset (usually larger) and a test dataset (smaller). Usually, this division uses around 80% of the data for model training, and the remaining 20% is used for testing and validating the models.

Then, with the available dataset, the different machine learning algorithms are explored to create classifiers, each with its strengths that can have better or worse results depending on the available data. Some of these possible algorithms are Support Vector Machines, and Artificial Neural Networks, among others [8]. After selecting the candidate algorithms, models are created with the trained dataset and tested using the test dataset. If any model is satisfactory, it is then selected and used to generate the predictions. If none of the models are acceptable, other algorithms, or the same ones with different parameterizations, can be used to develop new models.

3. Smart MES as an Enabler

Smart Manufacturing Execution Systems (Smart MES) such as RAILES can play a crucial role in integrating and using these predictive quality approaches due to their data extraction, harmonization, storage, and the ability to interoperate with different data sources and software tools. In a way, a Smart MES like RAILES can play the central role that facilitates the integration of these features, which are usually difficult to integrate and maintain. In an ideal case, the Smart MES can even provide all these functionalities, from data extraction and storage to generating forecasts using predictive models embedded in the Smart MES itself, facilitating the solution’s development, integration, and maintenance.

4. Industrial Application

In the context of the European project RAIZED [9], Muvu, in partnership with Vipex, developed a predictive quality solution for plastic injection molding machines. Muvu used its Smart MES – RAILES for data collection, pre-processing, labeling, and integrating functionalities to create and deploy the predictive models offered by the ZDMP platform [10]. Fig. 1 shows the system’s general architecture used and tested for three machines.

To evaluate the proposed solution’s performance, three Key Performance Indicators (KPIs), the Overall Equipment Effectiveness (OEE) [12], First Pass Yield (FPY), and Downtime. These KPIs were calculated before and after using the predictive quality solution. Fig. 2 shows the values of these KPIs before and after the solution, and it is possible to see an improvement in these KPIs.

 5. Conclusions

As was presented before, zero-defect production is essential to guarantee excellence in manufacturing. Therefore, AI can play a vital role in achieving this goal. In this post, it was possible to see how the process of creating a predictive quality solution is designed and the required steps. Besides these steps, other actions may happen when problems are related to a lack of data or poor data quality. Some techniques, such as feature selection or data augmentation, can mitigate these problems.

References

[1] MADE IN EUROPE – The manufacturing partnership in Horizon Europe (https://ec.europa.eu/info/sites/default/files/research_and_innovation/funding/documents/ec_rtd_he-partnership-made-in-europe.pdf)

[2] Peres, R. S., Jia, X., Lee, J., Sun, K., Colombo, A. W., & Barata, J. (2020). Industrial Artificial Intelligence in Industry 4.0-Systematic Review, Challenges and Outlook. IEEE Access, 8, 220121-220139.

[3] Melhem, M., Ananou, B., Ouladsine, M., & Pinaton, J. (2016). Regression methods for predicting the product’s quality in the semiconductor manufacturing process. IFAC-PapersOnLine, 49(12), 83-88.

[4] Kabasakal, İ., Keskin, F. D., Koçak, A., & Soyuer, H. (2019, August). A Prediction Model for Fault Detection in Molding Process Based on Logistic Regression Technique. In Proceedings of the International Symposium for Production Research 2019 (pp. 351-360). Springer, Cham.

[5] Zhang, S., Dubay, R., & Charest, M. (2015). A principal component analysis model-based predictive controller for controlling part warpage in plastic injection molding. Expert Systems with Applications, 42(6), 2919-2927.

[6] European Commission, Directorate-General for Research and Innovation, Renda, A., Schwaag Serger, S., Tataj, D. (2022). Industry 5.0, a transformative vision for Europe : governing systemic transformations towards a sustainable industry, Publications Office of the European Union. https://data.europa.eu/doi/10.2777/17322

[7] https://muvu.tech/the-role-of-equipment-communication-and-standards/

[8] Lorena, A. C., Jacintho, L. F., Siqueira, M. F., De Giovanni, R., Lohmann, L. G., De Carvalho, A. C., & Yamamoto, M. (2011). Comparing machine learning classifiers in potential distribution modelling. Expert Systems with Applications, 38(5), 5268-5275.

[9] https://muvu.tech/raized/

[10] https://www.zdmp.eu/

[11] https://muvu.tech/how-to-calculate-oee/

[12] Silva, B., Marques, R., Faustino, D., Ilheu, P., Santos, T., Sousa, J., & Rocha, A. D. (2023). Enhance the Injection Molding Quality Prediction with Artificial Intelligence to Reach Zero-Defect Manufacturing. Processes, 11(1), 62.