1 - 10 of 1941
-
PublicationVerschleißschutz einer Schneckengeometrie durch funktional gradierte Materialien( 2024-06)
-
PublicationAI-based welding process monitoring for quality control in large-diameter pipe manufacturing( 2024-04-25)The paper presents the experimental results into the development of a multi-channel system for monitoring and quality assurance of the multi-wire submerged arc welding (SAW) process for the manufacture of large diameter pipes. Process signals such as welding current, arc voltage and the acoustic signal emitted from the weld zone are recorded and processed to provide information on the stability of the welding process. It was shown by the experiments that the acoustic pattern of the SAW process in a frequency range between 30 Hz and 2.5 kHz contains the most diagnostic information. In the spectrogram of the acoustic signal, which represents the time course of the frequency spectrum of the welding process, the formation of weld irregularities such as undercuts could be reliably identified. The on-line quality assessment of the weld seam produced is carried out in combination with methods of artificial intelligence (AI). From the results obtained, it can be concluded that the use of the latest concepts in welding and automation technology, combined with the high potential of AI, can achieve a new level of quality assurance in pipe manufacturing.
-
PublicationImplementing human-robot collaboration in highly dynamic environments: Assessment, planning and development( 2024)Human-robot collaboration (HRC) applications have been slowly making their path in the industry. Although the required hardware and the methods for the planning and development of collaborative robotic applications are mostly already developed, some industrial branches still struggle to implement HRC. This is the case in motorcycle production, where, unlike car production, the assembly line has been optimized for manual work. Based on the use case described above, this paper identifies new requirements of HRC for automated screwing assembly operations in flexible production environments. In order to compensate deviations in the position of the tool relative to the workpiece, a screwing strategy based on force control is proposed. Parameter sensitivity is considered and supported experimentally with a screwing task performed by a cobot, where a method for contact detection between the nutrunner and the screw head is analyzed. This paper brings a guideline for experts from the manufacturing system engineering to implement HRC in highly dynamic assembly environments.
-
PublicationConcept for a modular system model for energy-efficiency monitoring of factory supply systems( 2024)Companies in the manufacturing industry are facing the challenges of both reducing energy costs as well as driving decarbonization. As a result, energy efficiency optimization of factory operations is gaining importance. Due to their high share in the energy consumption of a factory, industrial supply technology is of interest for these optimizations. Particularly cooling systems used in factories often offer considerable potential for energy efficiency improvements, some of which can be realized through optimized control strategies. Optimization based on control technology in particular requires a high level of energy consumption transparency in order to identify potentials and measure efficiency improvements. However, industrial supply systems are often complex and interconnected facilities composed of a combination of various individual assets. Consequently, the energy efficiency monitoring and analysis of such systems typically require a high manual effort. To reduce this effort, we propose the development of a modular system model which decomposes complex, interconnected energy systems to individual, recurring assets. The system model consists of a standardized data exchange format, a standardization of structural and behavioral models in the form of a model library for industrial supply systems at different hierarchy levels, and a standardized interface for using the data model on a target platform such as an energy management software. The data model of the data exchange format maps data points such as the control and media interfaces as well as energy performance indicators of the individual assets in a standardized and consistent way. Similar to the concept of digital twins, the knowledge of manufacturers and operators about the system is to be seamlessly combined and utilized. By connecting the interfaces of the individual asset models, an aggregate structural model of a factory supply system is built. The aggregate structural model enables the calculation of consistent and comparative energy performance indicators at equipment and system level. In this way, the implementation of energy efficiency monitoring and the assessment of energy efficiency potentials and improvements is facilitated. The system model concept is demonstrated using an industrial cooling system comprising individual assets such as a cooling tower, a chiller and pumps.
-
PublicationInteraction of Artificial Intelligence and Machining Processes Regarding Industry 4.0 Production Systems( 2024)Artificial intelligence (AI) has already been the subject of extensive scientific and industrial research in order to solve current challenges in intelligent manufacturing. However, these approaches often do not yet reach industrial small and medium-sized enterprises (SMEs). To meet the demand for resilient and sustainable production processes, the aim is to develop concepts to transfer applications into cyber physical production systems. Therefore, AI methods can be introduced as part of a smart manufacturing chain. In this work, an infrastructure to efficiently handle production data which is independent of the individual production process such as machining, grinding or electrical discharge machining is presented. Subsequently, an exemplary roadmap for SMEs is given to establish AI applications within the scope of manufacturing industry 4.0. As a result, an increase in efficiency and profitability of individual production processes as well as the overall production chain can be achieved.
-
PublicationAdvancing sustainable and efficient industrial cleaning: CO2 snow jet blasting for residue-free surface cleaning( 2024)
-
PublicationLimitations of Anomaly Detection: Beyond which Size Defects can be Reliably Recognized( 2024)Anomaly detection is one of the most popular fields for computer vision in industrial applications. The idea of training machine learning only on defect-free objects saves enormous amounts of integration effort. The state of the art shows that current methods on public data sets (e.g. MVTec AD data set) have already solved the problem with AUROC segementations scores of more than 99 %. But how accurate are these methods really? In this paper, one current method from the field of supervised learning and anomaly detection is evaluated on two problems. Each problem contains a defect pattern that grows in 11 steps. This work shows that the defect is already reliably detected from a relative size of 0.03 % of the pixels in the image.
-
PublicationDynamic error characteristics of robot motion analyzed for the suitability of visual-servoing( 2024)The knowledge of the absolute positioning accuracy of a robotic arm is crucial to assess the feasibility of certain tasks. In evaluating the feasibility, a robot manipulator as well as a possibly external sensing system must be chosen. In choosing a robot arm, lightweight robots are often preferred because they require less safety precautions, but they can also be less accurate compared to a stiff industrial robot. A stiff industrial robot resists external loads better, resulting in a higher accuracy with payload or process forces, and oscillates less in motions. Additionally, typical robot inaccuracies must be considered: (i) absolute positioning errors due to kinematic model errors, (ii) error due to resonance or external forces, (iii) path-following errors from limitations in the dynamic model and control. For tasks where the goal object has an unknown or varying pose, its pose can be measured with a vision system and used to compensate the robot motion. When the measurement and compensation is done continuously, it realizes closed-loop visual servoing. This can reduce the absolute error, but only the components of the error which are of a low frequency relative to the motion control bandwidth of the robot. To evaluate whether a specific robot can meet a certain accuracy requirements with a visual servoing system, better understanding about the characteristics of the robot error is needed. For example, the frequency distribution of the robot error can indicate what proportion can be compensated with closed loop control - only that less than the position bandwidth of the robot (typically 3-7 Hz). Datasheets typically provide the accuracy value only for repeatability while the accuracy during motion and the influence of dynamic effects are ignored. If the endeffector oscillates during motion causing a positional error and at which frequency is typically not reported - leaving unanswered, if it can be compensated by control. The contribution of this paper is the experimental evaluation of an absolute accuracy during the robot motion, towards evaluating the accuracy with a visual servoing system. A tracker system is used to collect the motion data of a CNC milling machine, a Universal Robots UR5, and an industrial robot (Comau Racer7-1.4) under various motion speeds. The frequency distribution and histograms of the error are analysed with regard to possible sources and the suitability to reduction with visual servoing.
-
PublicationSustainability transformation challenges for manufacturing companies and their employees: An approach how a serious game prepares and fosters the transformation( 2024)Besides the transformation process challenge towards intelligent networked production systems, the growing demand for the topic sustainability, which is integrated with the production process, creates an additional complex challenge for manufacturing companies. The industrial transformation process with regard to the focus of the fourth industrial revolution is enlarged in terms of the inquiry of sustainability and especially the circular economy. In particular, external political, economic and environmental factors, but at the same time society changes towards a sustainable mindset of people shape the future development. This article focuses on the question of how to sensitize and qualify employees of manufacturing companies with a serious game to start the preparation of the upcoming challenges regarding sustainable transformation. Starting from an optimized holistic production system as a start setting, currently discussed topics will be added as scenarios to teach and build up abilities to be prepared and face upcoming challenges.
-
PublicationData augmentation for inertial sensor based human action recognition using deep learning( 2024)Human Activity Recognition (HAR) approaches are predominantly based on supervised deep learning and benefit from large amounts of labeled data - an expensive resource. Data augmentation enriches labeled datasets by adding synthetic data, which is substantially cheaper, and often results in improved model performance, but is very rarely used for sensor data. This work explores data augmentation for inertial-sensor-based HAR by transforming the data through physically interpretable operations. The main studies were conducted on the Opportunity and the Overhead Car Assembly (OCA) datasets. For these experiments, only 20% of the available training data were used, and the experiments were conducted in an 8-fold cross-validation procedure over different subsets of the training data. The results show that simple geometric augmentations can be beneficial in many cases. Timewarping proved to offer the most reliable single augmentation, improving the average F1 score of Opportunity from 0.570 to 0.597 and of OCA Mixed from 0.884 to 0.906. Combining augmentations improved the accuracy in almost all scenarios but to a degree comparable to timewarping. Applying augmentations on all the available training data improved the F1 score compared to the base case with no augmentations, although this effect is more pronounced for datasets with more similar training and test data: for the OCA Mixed variant, the average F1 score improved from 0.917 to 0.933, while for the OCA Leave-One-Out (LOT) variant, the average F1 score did not significantly change. For Opportunity, which similarly to OCA LOT uses a participant-based training-test split, the F1 score improved from 0.684 to 0.697.
