In this study, we developed a deep learning-based real-time fault diagnosis system to automate the weaving preparation process in textile manufacturing. By analyzing typical faults such as shaft eccentricity and rotational imbalance, we designed a data-driven fault diagnosis algorithm. We utilized tension data from both normal and faulty states to implement AI-based diagnostic models, including 1D CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), and LSTM-AE (Long Short-Term Memory Autoencoder). These models enable real-time fault classification, followed by a comparative performance analysis. The LSTM-AE model achieved the best performance, with a classification accuracy of 99-100% for severe faults, such as 1.5 mm eccentricity and 100 or 150 g rotation imbalance, and 92.2% for minor faults like 1 mm eccentricity. This accuracy was optimized through threshold adjustments based on ROC curve analysis to select an optimal threshold. Building on these findings, we developed a GUI (Graphical User Interface) system capable of real- time fault diagnosis using TCP/IP (Transmission Control Protocol/Internet Protocol) communication between Python and LabVIEW. The results of this study are expected to accelerate the smartization of the weaving preparation process, contributing to improved textile quality and reduced defect rates, while also serving as a model for automation in other sectors.
In the semiconductor manufacturing industry, efficient operation of wafer transfer robots has a direct impact on productivity and product quality. Ball screw misalignment anomalies are a critical factor affecting precision transport of robots. Early diagnosis of these anomalies is essential to maintaining system efficiency. This study proposed a method to effectively diagnose ball screw misalignment anomalies using 1D-CNN and 2D-CNN models. This method mainly uses binary classification to distinguish between normal and abnormal states. Additionally, explainable artificial intelligence (XAI) technology was applied to interpret diagnostic decisions of the two deep learning models, allowing users to convince prediction results of the AI model. This study was based on data collected through acceleration sensors and torque sensors. It compared accuracies of 1D-CNN and 2D-CNN models. It presents a method to explain the model"s predictions through XAI. Experimental results showed that the proposed method could diagnose ball screw misalignment anomalies with high accuracy. This is expected to contribute to the establishment of reliable abnormality diagnosis and preventive maintenance strategies in industrial sites.
To develop a technology to diagnose the fault of dampers applied to railway vehicles and to set criteria, test runs were performed to measure damping force and displacement acting on a lateral damper during vehicle operation. Normal damper and fault damper were installed on a test train. Damper force and velocity of the lateral damper during test running were measured. Distributions of damper force and velocity representing the state of the damper had the same distribution in repeated tests. Distribution of the damper force and velocity was consistently uniform regardless of the train driving direction. Thus, the effect of train driving direction on damper force and velocity distribution was insignificant. The fault of the damper appeared to have a direct effect on the distribution of the damper force, suggesting that the fault of the damper could be sufficiently diagnosed just by monitoring the force of the damper. Especially, when comparing the velocity-force distribution, the fault damper showed a clear difference from a normal damper. Results of this paper could be used for developing a technology for diagnosing damper fault for railway vehicles in the future.
A clean room is used for adjusting the concentration of suspended particles using an air-conditioner. It has a fan-filter unit combining a centrifugal fan and a high-efficiency particulate air filter that purifies the outside air and directly affects its cleanliness. Defects in these systems are typically detected using special sensors for each fault, which can be costly. Therefore, this paper proposes a system for diagnosing defects in the fan-filter unit using a single differential sensor and deep learning. The fan-filter unit is part of the air-conditioning system, and it is usually defective in bearings, filters, and motors. These faults include ball wear, internal bearing contamination, filter contamination, and motor speed changes. Each defect was artificially induced in experiments, and the differential pressure data of each defect was learned using a long short-term memory (LSTM) deep learning algorithm. The results of deep learning experiments generated by randomly mixing data five times were presented using a confusion matrix, and the results showed an accuracy of 87.2±2.60%. Therefore, the possibility of diagnosing defects in the fan-filter unit using a single sensor was confirmed.
This paper proposes a high-fidelity finite element model of a permanent synchronous motor (PMSM) to predict electromagnetic responses. The proposed method aims to generate electromagnetic responses from the PMSM under various operational conditions-including normal and faulty conditions-by coupling several partial differential equations governing the electromagnetics of a PMSM. The rotor eccentricity is considered to be a representative fault of a PMSM, which has electromagnetic characteristics that differ from the healthy state of a PMSM. Note that eccentricity is the most frequent fault during PMSM operation. Therefore, the proposed model could replicate the defected torque responses of an actual motor system. The effectiveness of the proposed model is validated using measurements from a PMSM test bench. Quantitative comparison reveals that the proposed model could replicate both the transient- and steady-state torque responses of the PMSM of interest at a variety of operational conditions, including a faulty status. The proposed model could be used to generate virtual electromagnetic responses of a PMSM, which could be used for data-driven fault detection methods of electric motor systems.
Lithium-ion batteries are one of the main parts of electrical devices and are widely used in various applications. To safely use lithium-ion batteries, fault diagnosis and prognosis are significant. This paper analyzes resistance parameters from electrochemical impedance spectroscopy (EIS) to detect the fault of lithium-ion batteries. The internal fault mechanisms of batteries are so complex; it is difficult to detect abnormalities by direct current-based methods. However, by using alternating-current-based impedance by EIS, the internal degradation processes of the batteries can be detected. Impedance variation from EIS is verified under accelerated degradation test conditions and normal cycling test conditions. The results showed a significant relationship between fault and increase in resistance.
Citations
Citations to this article as recorded by
Research into the Detection of Faulty Cells in Battery Systems Using BMS Cell Balancing Counts Hyunjun Kim, Woongchul Choi Transaction of the Korean Society of Automotive Engineers.2025; 33(8): 637. CrossRef
PEDOT:PSS‐Based Prolonged Long‐Term Decay Synaptic OECT with Proton‐Permeable Material, Nafion Ye Ji Lee, Yong Hyun Kim, Eun Kwang Lee Macromolecular Rapid Communications.2024;[Epub] CrossRef
Lithium-Ion Batteries (LIBs) Immersed in Fire Prevention Material for Fire Safety and Heat Management Junho Bae, Yunseok Choi, Youngsik Kim Energies.2024; 17(10): 2418. CrossRef
A smart factory with Big Data analytics is getting attention because of its ability to automate and make the manufacturing environment more intelligent. At the same time, higher reliability is required with a drastic increase in complexity and uncertainty within the current system of manufacturing fields. The pump is considered as one of the most crucial equipment as it can affect the overall manufacturing performance of the manufacturing processes and it needs to be timely diagnosed of its mechanical condition as a top priority. In this research, we propose an operation system of centrifugal pumps and a data-driven fault diagnostic model that is developed by collecting relevant multivariate data from several natures. Proposed machine learning models can be used for detecting and diagnosing pump faults via analytical processes containing signal preprocessing and feature engineering procedures. Simulation and case studies from rotating machinery have demonstrated the effectiveness of the proposed analytical framework not only for attaining quantitative reliability but practical usages in actual manufacturing fields as well.
Citations
Citations to this article as recorded by
A Study on 3D Printing Conditions Prediction Model of Bone Plates Using Machine Learning Song Yeon Lee, Yong Jeong Huh Journal of the Korean Society for Precision Engineering.2022; 39(4): 291. CrossRef
Deep Learning-Based Analysis for Abnormal Diagnosis of Air Compressors Mingyu Kang, Yohwan Hyun, Chibum Lee Journal of the Korean Society for Precision Engineering.2022; 39(3): 209. CrossRef
A Cost-Aware DNN-Based FDI Technology for Solenoid Pumps Suju Kim, Ugochukwu Ejike Akpudo, Jang-Wook Hur Electronics.2021; 10(19): 2323. CrossRef
Commercial air-conditioning systems are widely used for buildings of various sizes. Design and installation of these systems follow a certain guideline developed by the manufacturer. The guideline also includes the adequate amount of refrigerant to be charged into the system. However, the guideline is often insufficient to reflect all the characteristics of installation, which results in too little or too much refrigerant. Inadequate amount of refrigerant usually causes more power consumption and reduced air-conditioning / heating capacity. This paper focuses on identifying the relationship between adequate refrigerant amount and various state variables such as condensation temperature of the air-conditioning system. This is based on regression analysis of data obtained through the experiments under controlled temperature and humidity.
Citations
Citations to this article as recorded by
Review of the advances and applications of variable refrigerant flow heating, ventilating, and air-conditioning systems for improving indoor thermal comfort and air quality Napoleon Enteria, Odinah Cuartero-Enteria, Takao Sawachi International Journal of Energy and Environmental Engineering.2020; 11(4): 459. CrossRef
The Smart Factory Equipment Engineering System collects and monitors necessary information in real-time. While putting the product into the equipment, operation conditions are lowered through a Recipe Management System. The working conditions are set by Run-to-Run a system for real-time detection and control through Fault Detection Classification function. In this study, the smart factory equipment system associated with the entire system is proposed by defining and integrating the necessary equipment management functions from a smart factory’s point of view. To do this, detailed analysis and process improvement on products, processes, and production line equipment were conducted and implemented in the smart factory equipment engineering system. The models proposed in this paper have been implemented to the production site of BGA-PCB. It has been confirmed that the models have resulted in significant change, and have qualitative and quantitative impacts on the working methods of equipment. Typically, data collection time, data entry time, and manual writing sheets were greatly reduced.
Fault diagnosis and condition monitoring of rotating machines are important for the maintenance of the gas turbine system. In this paper, the Lab-scale rotor test device is simulated by a gas turbine, and faults are simulated such as Rubbing, Misalignment and Unbalance, which occurred from a gas turbine critical fault mode. In addition, blade rubbing is one of the gas turbine main faults, as well as a hard to detect fault early using FFT analysis and orbit plot. However, through a feature based analysis, the fault classification is evaluated according to several critical faults. Therefore, the possibility of a feature analysis of the vibration signal is confirmed for rotating machinery. The fault simulator for an acquired vibration signal is a rotor-kit based test rig with a simulated blade rubbing fault mode test device. Feature selection based on GA (Genetic Algorithms) one of the feature selection algorithm is selected. Then, through the Support Vector Machine, one of machine learning, feature classification is evaluated. The results of the performance of the GA compared with the PCA (Principle Component Analysis) for reducing dimension are presented. Therefore, through data learning, several main faults of the gas turbine are evaluated by fault classification using the SVM (Support Vector Machine).
Citations
Citations to this article as recorded by
A Study on Machine Learning-Based Feature Classification for the Early Diagnosis of Blade Rubbing Dong-hee Park, Byeong-keun Choi Sensors.2024; 24(18): 6013. CrossRef
Feature selection and feature learning in machine learning applications for gas turbines: A review Jiarui Xie, Manuel Sage, Yaoyao Fiona Zhao Engineering Applications of Artificial Intelligence.2023; 117: 105591. CrossRef
Simultaneous Fault Diagnostics for Three-Shaft Industrial Gas Turbine Waleligne Molla Salilew, Syed Ihtsham Gilani, Tamiru Alemu Lemma, Amare Desalegn Fentaye, Konstantinos G. Kyprianidis Machines.2023; 11(8): 832. CrossRef
A Machine Learning-Based Signal Analytics Framework for Diagnosing the Anomalies of Centrifugal Pumps Kang Whi Kim, Jihoon Kang, Seung Hwan Park Journal of the Korean Society for Precision Engineering.2021; 38(4): 269. CrossRef
Performance Improvement of Feature-Based Fault Classification for Rotor System Won-Kyu Lee, Deok-Yeong Cheong, Dong-Hee Park, Byeong-Keun Choi International Journal of Precision Engineering and Manufacturing.2020; 21(6): 1065. CrossRef
A paper cup forming machine performs the entire process to produce paper cups. Recently, as the demand for paper cups in various fields increases, the need for rapid and timely paper cup forming also increases. However, the more rapid the manufacturing speed is, the higher the possibility of forming failure. Frequent fault occurrences cause a time-consuming and costly repair process and reduces manufacturing efficiency. Among various fault factors in this research, position deviation of the paper from the original position, which induces a jamming and process stop, was selected and a novel deviation detecting system using multiple photo sensors was suggested. Before operating the position detecting system, the performance of the photo sensors was evaluated with respect to response speed and photo beam precision. A deviation detecting mechanism was designed. The developed deviation detecting system was integrated with the paper cup forming machine and experimented with using base papers. It was conformed that the suggested system could be used to diagnose paper deviation failure.
Citations
Citations to this article as recorded by
The Development of a Failure Diagnosis System for High-Speed Manufacturing of a Paper Cup-Forming Machine Seolha Kim, Jaeho Jang, Baeksuk Chu Journal of the Korean Society of Manufacturing Process Engineers.2019; 18(5): 37. CrossRef
First
Prev
