Steinberg, Fabian
7 results
Now showing 1 - 7 of 7
- Some of the metrics are blocked by yourconsent settings
Publication Access status: Open Access , Approaches for the prediction of lead times in an engineer to order environment - a systematic reviewThe interest of manufacturing companies in a sufficient prediction of lead times is continuouslyincreasing - especially in engineer to order environments with typically a large number of individual parts andcomplex production processes. A multitude of approaches have been proposed in the literature for predictinglead times considering different data and methods or algorithms from operations research (OR) and machinelearning (ML). In order to provide guidance at setting up prediction models and developing new approaches,a systematic review of the available approaches for predicting lead times is presented in this paper. Forty-twopublications were analyzed and synthetized: Based on a developed framework considering the used dataclass (e.g. product data or system status), the data origin (master data or real data) and the used methodand algorithm from OR and ML, the publications are classified. Based on the classification, a descriptiveanalysis is performed to identify common approaches in the existing literature as well as implications forfurther research. One result is, that mostly order data and the status of the production system are used forpredicting lead times whereas material data are used seldom. Additionally, ML approaches primarily useartificial neural networks and regression models for predicting lead times, while OR approaches use mainlycombinatorial optimization or heuristics. Furthermore, with increasing model complexity the use of realdata decreased. Thus, we identified as an implication for further research to set up a complex data modelconsidering material data, which uses real data as data origin.Source Type:Article4 15 - Some of the metrics are blocked by yourconsent settings
Publication Access status: Metadata only , Bridging human expertise and machine learning in production management: a case study on ML-based decision support systems to prevent missing parts at assemblyIn the field of production management, decision support systems (DSS) equipped with machine learning (ML) have significantly advanced production planning and control within manufacturing companies. These systems are crucial, particularly in the machinery industry, for predicting shortages such as missing parts at the start of assembly. However, current ML-based DSS typically focus solely on predicting occurring problems or suggesting options for simplified scenarios, often missing the critical integration of human operators in the decision-making loop. This study introduces an advanced DSS that integrates ML to predict a missing part for the assembly start and to automatically provide a clear indication of the causes behind predicted shortages. This is achieved by employing shapley additive explanations (SHAP) to the respective ML-based prediction model. Thus, this analysis enables production controllers to initiate both proactive and/or reactive actions by detailed insights into the system’s predictions, and fostering a more dynamic interaction providing between human decision-makers and automated systems. This integration reduces the reliance on time-consuming manual analyses and enhances transparency in decision-making processes. The efficacy of the integrated approach is demonstrated by a case study conducted at a German machinery manufacturer, specialized in low-volume, high-variety production. The findings of this case study confirm that the DSS is efficacious in supporting complex decision-making processes, making it a valuable tool for modern production environments.Source Type:Article3 - Some of the metrics are blocked by yourconsent settings
Publication Access status: Metadata only , Enhancing brewery logistics with smart kegs: A simulation studyBackground: Supply chain optimisation is critical for companies in today’s globalised world. Efficient supply chains ensure product quality and freshness in the food industry. For products like beer, efficiency extends beyond transportation and includes the management of logistics containers such as returnable kegs.Objectives: This study investigated the impact of tracking logistics data on the efficiency of container logistics in a small regional brewery. The focus was reducing fleet size, processing times and pick-up distances.Method: A simulation of a small brewery was used to analyse the impact of tracking logistics data. The study examined how kegs equipped with real-time tracking technology could improve logistics operations.Results: The simulation showed that tracking logistics data significantly improved logistics processes. It led to a reduction in the fleet size, turnaround times and pick-up distances for empty kegs. These improvements were attributed to better resource allocation and more efficient management of reusable containers.Conclusion: The study showed that smart kegs could reduce logistical inefficiencies in the brewing industry. The use of smart technologies in container logistics improves operational efficiency and sustainability.Contribution: This research provides insights into how smart technologies can transform traditional logistics models. The results suggest that smart containers can revolutionise supply chains with efficient resource allocation, real-time tracking and automation. This shift towards smart logistics aligns with the broader adoption of the Industrial Internet of Things, offering a blueprint for future innovations in supply chain management. The implications extend beyond brewing, highlighting the potential for greater sustainability and a positive reduction in environmental impact in global supply chains.Source Type:Article3 - Some of the metrics are blocked by yourconsent settings
Publication Access status: Metadata only , Machine learning implementation in small and medium-sized enterprises: insights and recommendations from a quantitative studyMachine learning (ML) offers high potential in manufacturing industry; moreover, for example the effectiveness of quality prediction and evaluation can be greatly improved using Machine Learning, which can generate significant competitive advantages. However, the potentials of ML are not fully exploited by small and medium-sized enterprises. A qualitative empirical study was conducted with 60 companies from different industry sectors to determine when SMEs are more likely to use ML. Here, it is shown that the willingness to invest in applications is substantial for the implementation of ML. Also, the availability of sufficient qualitative data within the SME is imperative for applying ML. Furthermore, recommendations for action for SMEs are established to close the technology adoption gap in SMEs and to leverage the benefits of ML.Source Type:Article2 - Some of the metrics are blocked by yourconsent settings
Publication Access status: Open Access , Machine learning-based prediction of missing components for assembly - a case study at an engineer-to-order manufacturerFor manufacturing companies, especially for machine and plant manufacturers, the assembly of products in time has an essential impact on meeting delivery dates. Often missing individual components lead to a delayed assembly start, hereinafter referred to as assembly start delayers. Identifying the assembly start delayers early in the production process can help to set countermeasures to meet the required delivery dates. In order to achieve this, we set up 24 prediction models on four different levels of detail utilizing different machine learning-algorithms - six prediction models on every level of detail - and applying a case-based research approach in order to identify the model with the highest model quality. The modeling approach on the four levels of detail is different. The models on the coarsest level of detail predict assembly start delayers utilizing a classification approach. The models on the three finer levels of detail predict assembly start delayers via a regression of different lead times and subsequent postprocessing operations to identify the assembly start delayers. After training of the 24 prediction models based on a real data set of a machine and plant manufacturer and evaluating their model quality, the classification model utilizing a Gradient Boosting classifier showed best results. Thus, performing a binary classification to identify assembly start delayers was the best modelling approach. With the achieved results, our study is a first approach to predict assembly start delayers and gives insights in the performance of different modeling approaches in the area of a production planning and control.Source Type:Article2 9 - Some of the metrics are blocked by yourconsent settings
Publication Access status: Open Access , Machine learning-based prediction of missing parts for assembly(2024)Manufacturing companies are faced with the challenge of managing increasing process complexity, while at the same time having to meet ever higher demands in terms of on-time delivery and product costs. Especially at points in the value chain such as assembly, where different material flows converge, it is often not possible to provide the components required for an order in a timely and synchronized manner. Early identification of missing parts at the beginning of assembly can help to take countermeasures to meet the required delivery dates. To achieve this, this thesis develops machine learning based prediction models that can predict potential missing parts at the start of assembly at an early stage in the value chain. The development of the models was carried out as case studies at manufacturing companies in the machine industry. As a basis for the development, an extensive systematic literature search was conducted on existing approaches for the prediction of lead times of production orders. The result was that no approach exists that takes into account the full complexity of manufacturing companies. In particular, with regard to the data used, it became clear that information about the product to be manufactured—so-called material data—has not been used up to now. Based on the systemic review, a model for predicting missing parts from inhouse production was implemented. It was shown that classification approaches achieve the best possible model quality for components from in-house production. With the defined modeling approach—classification—it was then verified that material data has a significant influence on the model quality and is therefore relevant for the prediction of missing parts at the start of assembly. Finally, a model for predicting delivery delays in the purchasing process was implemented, which makes it possible to predict potential missing parts from suppliers at the time of ordering. The case studies show that the use of machine learning for the prediction of missing parts in both in-house production and the purchasing process can identify delays in the start of assembly at an early stage. The developed models are therefore suitable as a support system for production planners and controllers as well as purchasing departments to improve material availability at the start of assembly.Source Type:Doctoral Thesis5 16 - Some of the metrics are blocked by yourconsent settings
Publication Access status: Metadata only , 1
