Burggräf, Peter
14 results
Now showing 1 - 10 of 14
- Some of the metrics are blocked by yourconsent settings
Publication Access status: Open Access , A clustering approach for topic filtering within systematic literature reviewsWithin a systematic literature review (SLR), researchers are confronted with vast amounts of articles from scientific databases, which have to be manually evaluated regarding their relevance for a certain field of observation. The evaluation and filtering phase of prevalent SLR methodologies is therefore time consuming and hardly expressible to the intended audience. The proposed method applies natural language processing (NLP) on article meta data and a k-means clustering algorithm to automatically convert large article corpora into a distribution of focal topics. This allows efficient filtering as well as objectifying the process through the discussion of the clustering results. Beyond that, it allows to quickly identify scientific communities and therefore provides an iterative perspective for the so far linear SLR methodology. • NLP and k-means clustering to filter large article corpora during systematic literature reviews. • Automated clustering allows filtering very efficiently as well as effectively compared to manual selection. • Presentation and discussion of the clustering results helps to objectify the nontransparent filtering step in systematic literature reviews.Source Type:Article2 4 - Some of the metrics are blocked by yourconsent settings
Publication Access status: Metadata only , AI-artifacts in engineering change management – a systematic literature reviewChanges and modifications to existing products, known as engineering changes (EC), are common in complex product development. They require appropriate implementation planning and supervision to mitigate the economic downsides due to complexity. These tasks, however, take a high administrative toll on the organization. In response, automation by computer tools has been suggested. Due to the underlying process complexity, the application of artificial intelligence (AI) is advised. To support research and development of new AI-artifacts for EC management (ECM), a knowledge base is required. Thus, this paper aims to gather insights from existing approaches and discover literature gaps by conducting a systematic literature review. 39 publications applying AI methods and algorithms in ECM were identified and subsequently discussed. The analysis shows that the methods vary and are mostly utilized for predicting change propagation and knowledge retrieval. The review’s results suggest that AI in EC requires developing distributed AI systems to manage the ensuing complexity. Additionally, five concrete suggestions are presented as future research needs: Research on metaheuristics for optimizing EC schedules, testing of stacked machine learning methods for process outcome prediction, establishment of process supervision, development of the mentioned distributed AI systems for automation, and validation with industry partners.Source Type:Article4 - 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: Open Access , Bibliometric study on the use of machine learning as resolution technique for Facility Layout ProblemsFacility Layout Problems (FLP) are concerned with finding efficient factory layouts. Numerous resolution approaches are known in literature for layout optimization. Among those, intelligent approaches are less researched than solutions from exact or approximating approaches. The recent surge of research interest in Artificial Intelligence, and specifically Machine Learning (ML) techniques, presages an increase of such techniques' usage in FLP. However, previous reviews on FLP research induce that, to date, this trend has not yet emerged. Utilizing a systematic literature review coupled with a k-Means based clustering algorithm, we analyzed 25 relevant publication full-texts from an original sample of 1,425 papers. Our findings corroborate the statement that ML techniques have attracted substantially less research interest than most other resolution approaches. While a few papers used Unsupervised Learning algorithms directly as a solution to the FLP, Supervised and Reinforcement Learning were found to be practically irrelevant. ML usage was significantly higher in FLP-adjacent planning tasks such as group technology. Drawing from experiences with other NP-hard combinatorial optimization problems in manufacturing research, we conclude that Reinforcement Learning is most promising to bridge the evident gap between FLP and ML research. Our study further contributes to FLP research by extending established classification frameworks.Source Type:Article407 290 - 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: Open Access , Data on the current state of problem solving and improvement during physical product development within complex (manufacturing) systems(2019); ; Due to the exponential increase of failure cost during the product development process, problems have to be effectively remedied as early as possible and with shortened innovation cycles, increasingly efficient. For the manufacturing of complex products at low maturity levels (referred to as physical product development), nonconformance problem solving constitutes a major difficulty in this regard (Camarillo et al., 2017; Walter et al., 2010). The data presented in this article was collected from German companies, differing in size and industry sector, manufacturing highly complex products at low maturity. Selected and consulted companies therefore operate in (or comparable to) the automotive prototyping, air and space, shipbuilding, special machinery or electronics domain. The survey comprises the answers of 46 participants, gathered via online questionnaire. It subdivides into 18 questions covering the companies’ characteristics, knowledge management and documentation systems within the product development process, as well as the appraisal of technological potentials. The obtained data gives an insight into the industrial status quo of nonconformance problem solving. The data allows to derive existing deficits and dedicated research on solutions.Source Type:Article316 110 - 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 , gym-flp: A Python Package for Training Reinforcement Learning Algorithms on Facility Layout ProblemsReinforcement learning (RL) algorithms have proven to be useful tools for combinatorial optimisation. However, they are still underutilised in facility layout problems (FLPs). At the same time, RL research relies on standardised benchmarks such as the Arcade Learning Environment. To address these issues, we present an open-source Python package (gym-flp) that utilises the OpenAI Gym toolkit, specifically designed for developing and comparing RL algorithms. The package offers one discrete and three continuous problem representation environments with customisable state and action spaces. In addition, the package provides 138 discrete and 61 continuous problems commonly used in FLP literature and supports submitting custom problem sets. The user can choose between numerical and visual output of observations, depending on the RL approach being used. The package aims to facilitate experimentation with different algorithms in a reproducible manner and advance RL use in factory planning.Source Type:Article2 - Some of the metrics are blocked by yourconsent settings
Publication Access status: Metadata only , Hybrid intelligence – systematic approach and framework to determine the level of Human-AI collaboration for production management use cases(2024); Artificial intelligence (AI) and machine learning (ML) have emerged as transformative technologies in production management, enhancing decision-making and operational efficiency across a range of use cases. The challenge of determining the optimal level of Human-AI collaboration in decision-making processes persists for many organizations, despite the potential benefits of such integration. However, the current systematic approaches frequently lack a structured approach to determine the level of Human-AI collaboration in production management use cases. This results in inconsistent applications and suboptimal outcomes. This study presents a first and superior systematic approach for the systematic evaluation, development and implementation of AI in production management and introduces a structured framework that can be employed to assess and determine the optimal level of Human-AI collaboration for a range of production use cases. The framework classifies use cases based on critical factors such as data availability, process variability, error susceptibility, and decision complexity. This classification assists managers in calibrating the balance between automation and human intervention. The application of this framework could enhance the efficacy, productivity, and accuracy of Human-AI collaboration in production management. Furthermore, the systematic approach incorporates continuous evaluation and adaptation, ensuring long-term success in dynamic production environments. These findings provide a practical tool for managers to strategically implement AI, improving decision-making processes and operational outcomes. The proposed framework offers immediate opportunities to enhance production management through a structured, scalable, and human-centered approach to AI integration.Source Type:Article1 - 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
