M. Carratù, V. Gallo, V. Laino, C. Liguori
Identification and morphological analysis of microorganisms are of high interest in scientific research, especially in the medical field and food industry. Identification allows rapid functional characterization based on similarities with known related species enabling to confirm the identity of an isolate used, for example, in a trademarked industrial process. Monitoring of microorganisms within a given ecosystem and analysis of the morphological characteristics of the observed species enable quality control of the process under analysis. Such procedures are carried out manually in...
TC10 Conference 2023
· TC10
· 2023
· 10.21014/tc10-2023.009
· Download
Yukio Hiranaka, Koichi Tsujino, Hidenori Katsumura, Masashi Nakagawa
Human Experts may diagnose the state of a rotating machine by listening to its vibration sounds. Variational Auto-encoder (VAE) is an alternative method to realize the diagnosis by AI learning. Previous studies have shown that when the normal state can be assumed to be a single Gaussian distribution, anomaly scores can be calculated as deviations from the center of the distribution in the VAE latent space. However, when the normal state consists of different modes corresponding to operating conditions, the calculation may not be a simple task. As a way to solve this problem, the use of...
TC10 Conference 2023
· TC10
· 2023
· 10.21014/tc10-2023.008
· Download
Roland Nagy, István Szalai
Vibrations in road vehicles can have highly harmful effects on both the vehicle components and the passengers. These vibrations are mainly caused by lowquality pavement, so it is important to keep the road network in good condition and to know its general quality. In our study, we present the development of a universally applicable, low-cost measurement system for the purpose of measuring the condition of pavement surfaces. The system can be used to identify road sections in urgent and near future need of maintenance, thus helping to schedule construction works efficiently. The system is...
TC10 Conference 2023
· TC10
· 2023
· 10.21014/tc10-2023.007
· Download
Bartosz Połok, Piotr Bilski
The following paper presents the methodology of monitoring the state of the ratchet mechanisms in the presence of noise. The fault detection is based on the acoustic analysis of the signals generated by the revolving mechanism. Decision is made using machine learning methods, which accuracy is compared. The object of the analysis is the ratchet mechanism installed in the actual BMX-type bicycle. It was shown that the noise suppression approach is suitable for the applied diagnostic framework, leading to the high accuracy in detecting catastrophic faults, such as breaking the tooth inside the...
TC10 Conference 2023
· TC10
· 2023
· 10.21014/tc10-2023.006
· Download
Marco Carratù, Vincenzo Gallo, Antonio Pietrosanto, Gabriele Patrizi, Alessandro Bartolini, Lorenzo Ciani, Marcantonio Catelani
The development and spread of Machine Learning methodologies have also involved the field of anomaly detection, particularly focused on fault detection. This is one of the main goals of Industry 4.0, as it is necessary to optimize repair time and cost. In this regard, Machine Learning is needed to identify precursor features of possible failures that would be difficult for a human operator to discern. However,compared to Deep Learning methodologies, these cannot be fully automatic because of the need to make choices about the features identified by the system. This paper aims to propose a...
TC10 Conference 2023
· TC10
· 2023
· 10.21014/tc10-2023.005
· Download
Leonhard Czarnetzki, David Karnok, Johannes Breitschopf, Matthias Karner, Milot Gashi, Thomas Mambrini, Catherine Laflamme, Viola Gallina, Wilfried Sihn
Accurate production planning is economic interest of manufacturing companies. Reducing the work-inprogress levels, the lead time or control efforts with the simultaneous increase of utilization and adherence to schedule might lead to instantaneous cost reduction and to increased competitiveness on long-term. In the era of digitization various artificial intelligence-based methods have been investigated by the scientific community to improve these key performance indicators. In this paper the results of a joint research project dealing with planning quality improvement with the help of...
TC10 Conference 2023
· TC10
· 2023
· 10.21014/tc10-2023.004
· Download
Eszter Kocsis, Attila Lukács, István Szalai
Flux is a necessity in the lead-free soldering process. Inactivated flux residues can cause electrical shortages and functional issues by ion migration. Because of miniaturization and the complexity of recent electronic products a cleaner manufacturing process is required. Atmospheric pressure plasma treatment (PT) is a commonly applied surface cleaning method in the manufacturing industry and has been proved to be effective in improving the wettability in case of metal and polymer surfaces. Three different types of printed circuit board (PCB) surface finishes were investigated before and...
TC10 Conference 2023
· TC10
· 2023
· 10.21014/tc10-2023.003
· Download
Henrik Heymann, Jan Hendrik Hellmich, Maik Frye, Dennis Grunert, Robert H. Schmitt
Artificial Intelligence (AI) projects in production often end in proof-of-concepts with AI solutions not being continuously maintained along their life cycle. Only by managing multiple AI use cases simultaneously and systematically, companies can achieve an industrial level of usage in their production environment and fully benefit from the technology’s potential. For that purpose, an AI management model is proposed that serves as a framework to capture, design, and optimize AI activities to continuously improve the quality of the AI solutions and the satisfaction of involved stakeholders....
TC10 Conference 2023
· TC10
· 2023
· 10.21014/tc10-2023.002
· Download
Chao-Ching Ho, Chun-Han Liu, Ming-Fu Chen, Ming-Chieh Kao
This paper proposes a multi-task learning system for industrial defect detection, focusing on surface scratches on titanium gaskets as the detection target. Our model is built using a deep convolutional neural network (CNN). As defects are infrequent in actual production lines, we adopt the Faster-RCNN object detection network architecture and integrate it with a multi-task learning system. A classification task model is introduced into the backbone network to filter out a significant number of defect-free images. This step reduces the computation and data transmission time of the subsequent...
TC10 Conference 2023
· TC10
· 2023
· 10.21014/tc10-2023.001
· Download
Patrik Jurík, Miroslav Sokol, Pavol Galajda
This article describes phase noise measurement of a designed ASIC voltage-controlled oscillator in 0.25 µm SiGe BiCMOS technology, with frequency synthesizer ADF4002 from Analog Devices. The oscillator topology utilized in this design is based on a crosscoupled-transistor configuration, and it incorporates two options for frequency control: varicap and capacitor bank. The oscillator frequency is 11.13 GHz with an adjustment frequency range around ±250 MHz. Phase noise measurements were performed on a custom evaluation board. Oscillator with PLL achieves phase noise λ(100 kHz)= -70 dBc at fc...
TC4 Symposium 2023
· TC4
· 2023
· 10.21014/tc4-2023.46
· Download