@article{KovalKnollmeyerMathiasetal.2024, author = {Koval, Leonid and Knollmeyer, Simon and Mathias, Selvine George and Asif, Saara and Akmal, Muhammad Uzair and Großmann, Daniel and Bregulla, Markus}, title = {Unlocking the Potential of Information Modeling for Root Cause Analysis in a Production Environment: A Comprehensive State-of-the-Art Review Using the Kitchenham Methodology}, volume = {12}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2024.3406020}, pages = {80266 -- 80282}, year = {2024}, abstract = {Data from production environments is now available in unprecedented volumes, making the problem-solving of incidents through root cause analysis straightforward. However, the root cause analysis process remains time-consuming. This study employs the Kitchenham standard systematic literature review methodology to explore how information models and deep learning can streamline this process. By conducting a comprehensive search across four major databases, we evaluate the current technological advancements and their application in root cause analysis. The aim of this study is to assesses the impact of information models for root cause analysis in a production environment. Our findings reveal that integrating knowledge graphs, association rule mining, and deep learning algorithms significantly improves the speed and depth of root cause analysis compared to traditional methods. Specifically, the use of neural networks in recent literature shows substantial advancements in analyzing complex datasets, facilitating large-scale data integration, and enabling automated learning capabilities. Comparing our findings with other recent studies highlights the advantages of using information modeling and deep learning technologies in root cause analysis. This comparison underscores the superior accuracy and efficiency of these advanced methodologies over traditional manual interpretation methods. The effective implementation of these technologies requires a robust foundation of clean, standardized data, giving rise to the concept of "Production IT." Furthermore, it is crucial for this data to be openly available to facilitate academic research, thereby enabling the development of new methods for more efficient and effective root cause analysis.}, language = {en} } @article{BilalPodishettiKovaletal.2024, author = {Bilal, M{\"u}henad and Podishetti, Ranadheer and Koval, Leonid and Gaafar, Mahmoud A. and Großmann, Daniel and Bregulla, Markus}, title = {The Effect of Annotation Quality on Wear Semantic Segmentation by CNN}, volume = {24}, pages = {4777}, journal = {Sensors}, number = {15}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {https://doi.org/10.3390/s24154777}, year = {2024}, abstract = {In this work, we investigate the impact of annotation quality and domain expertise on the performance of Convolutional Neural Networks (CNNs) for semantic segmentation of wear on titanium nitride (TiN) and titanium carbonitride (TiCN) coated end mills. Using an innovative measurement system and customized CNN architecture, we found that domain expertise significantly affects model performance. Annotator 1 achieved maximum mIoU scores of 0.8153 for abnormal wear and 0.7120 for normal wear on TiN datasets, whereas Annotator 3 with the lowest expertise achieved significantly lower scores. Sensitivity to annotation inconsistencies and model hyperparameters were examined, revealing that models for TiCN datasets showed a higher coefficient of variation (CV) of 16.32\% compared to 8.6\% for TiN due to the subtle wear characteristics, highlighting the need for optimized annotation policies and high-quality images to improve wear segmentation.}, language = {en} } @article{BilalPodishettiTangiralaetal.2025, author = {Bilal, M{\"u}henad and Podishetti, Ranadheer and Tangirala, Sri Girish and Großmann, Daniel and Bregulla, Markus}, title = {CNN-Based Classification of Optically Critical Cutting Tools with Complex Geometry: New Insights for CNN-Based Classification Tasks}, volume = {25}, pages = {1575}, journal = {Sensors}, number = {5}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {https://doi.org/10.3390/s25051575}, year = {2025}, abstract = {Sustainability has increasingly emphasized the importance of recycling and repairing materials. Cutting tools, such as milling cutters and drills, play a crucial role due to the high demands placed on products used in CNC machining. As a result, the repair and regrinding of these tools have become more essential. The geometric differences among machining tools determine their specific applications: twist drills have spiral flutes and pointed cutting edges designed for drilling, while end mills feature multiple sharp edges around the shank, making them suitable for milling. Taps and form cutters exhibit unique geometries and cutting-edge shapes, enabling the creation of complex profiles. However, measuring and classifying these tools for repair or regrinding is challenging due to their optical properties and coatings. This research investigates how lighting conditions affect the classification of tools for regrinding, addressing the shortage of skilled workers and the increasing need for automation. This paper compares different training strategies on two unique tool-specific datasets, each containing 36 distinct tools recorded under two lighting conditions—direct diffuse ring lighting and normal daylight. Furthermore, Grad-CAM heatmap analysis provides new insights into relevant classification features.}, language = {en} } @article{BilalPodishettiGrossmannetal.2025, author = {Bilal, M{\"u}henad and Podishetti, Ranadheer and Großmann, Daniel and Bregulla, Markus}, title = {Benchmarking CNN Architectures for Tool Classification: Evaluating CNN Performance on a Unique Dataset Generated by Novel Image Acquisition System}, volume = {13}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2025.3574785}, pages = {96400 -- 96422}, year = {2025}, abstract = {In this study, we introduce the ToolSurface-144 dataset, which is presented here for the first time. It comprises four subsets - Full R, Full S, Top R, and Top S - each containing 144 tool classes captured under varying illumination conditions and fields of view. A newly developed, patented imaging approach was employed to acquire the data. It is compared with conventional diffuse ring illumination to assess its effectiveness in evaluating state-of-the-art convolutional neural networks. This enabled a more targeted investigation of the role of global shape characteristics such as silhouettes versus localized features like the tool face, cutting edges, and delicate geometrical structures under different training strategies. In this study, we evaluate six state-of-the-art convolutional neural networks—AlexNet, DenseNet161, EfficientNet-B0, ResNet152, ResNet50, and VGG16—using three training strategies: fine-tuning, freezing of pre-trained layers, and training from scratch. The results show that EfficientNet-B0 consistently achieved the highest classification accuracy in nearly all experiments and data sets. Especially using the fine-tuning training strategy, the model achieved 99\% accuracy in tool classification. ResNet50 benefited greatly from fine-tuning and freezing, achieving a significant increase in performance compared to training from scratch. In contrast, ResNet152, AlexNet, and VGG16 consistently showed poor classification performance, indicating difficulties regarding learning and generalisation. The results show that diffuse illumination and complete tool views provide the best classification conditions, while restricted image sections with homogeneous illumination negatively affect model performance. Among the evaluated training strategies, fine-tuning proved the most efficient training method for developing CNN models for tool classification.}, language = {en} } @article{BilalPodishettiKovaletal.2024, author = {Bilal, M{\"u}henad and Podishetti, Ranadheer and Koval, Leonid and Gaafar, Mahmoud A. and Großmann, Daniel and Bregulla, Markus}, title = {Automatized End Mill Wear Inspection Using a Novel Illumination Unit and Convolutional Neural Network}, volume = {12}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2024.3454692}, pages = {124282 -- 124297}, year = {2024}, abstract = {Ensuring cutting tools are in optimal condition is essential for achieving peak machining performance, given their direct impact on both workpiece quality and process efficiency. However, accurately assessing wear on end mills, especially those with complex geometries, pose a significant challenge due to their reflective surfaces and varied wear patterns. Presented here is a novel method that addresses this challenge by employing a customized illumination unit in conjunction with a convolutional neural network (CNN) for end mill wear analysis. This innovative approach involves utilizing the specially designed illumination unit to capture high-quality images, enabling precise examination of material wear on helically shaped end mills. Notably, this method is tailored to illuminate reflective surfaces and represents a pioneering application in the realm of wear testing.We validate the viability of this approach by employing CNN-based models to segment wear on complex-shaped end mills coated with titanium carbonitride (TiCN) and titanium nitride (TiN). We achieved remarkable mean Intersection over Union (mIoU) results in wear detection on a test dataset: 0.99 for tool segmentation, 0.78 for abnormal wear, and 0.71 for normal wear segmentation.}, language = {en} }