• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.801-807
• /
• 2024

Linear motion robots are devices that perform functions such as transferring parts or positioning devices, and require high precision. In companies that develop linear robot application systems, human workers are in charge of quality control and fault diagnosis of linear robots, and the result and accuracy of a fault diagnosis varies depending on the skill level of the person in charge. Recently, there have been many attempts to utilize artificial intelligence to diagnose faults in industrial devices. In this paper, we present a system that automatically diagnoses linear rail and ball screw misalignment of a linear robot using transfer learning. In industrial systems, it is difficult to obtain a lot of learning data, and this causes a data imbalance problem. In this case, a transfer learning model configured by retraining an established model is widely used. The information obtained by using an acceleration sensor and torque sensor was used, and its usefulness was evaluated for each case. After converting the signal obtained from the sensor into a spectrogram image, the type of abnormality was diagnosed using an image recognition artificial intelligence classifier. It is expected that the proposed method can be used not only for linear robots but also for diagnosing other industrial robots.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.127-130
• /
• 2004

For the quality control of the industrial products, an automatic hole measuring system has been developed. The measurement device allows X-Y movement due to contact forces between a hole and its own circular cone and the device is attached to an industrial robot. Its measurement accuracy is about 0.04mm. This movement of the plate is measured by two LVDT sensor system. But this system using the LVDT sensors is restricted by high cost and precision of measurement and correspondence of environment so particularly, a vision system with CCD-Camera is discussed in this paper for the above mentioned purpose. The device consists of two of two links jointed with hinge pins basically and, they guarantee free movement of the touch prove attached on the second link in the same plane. These links are returned to home position by the spring plungers automatically after each process for the next one. On the surface of the touch prove, it has a circular white mark for camera recognition. The system detect and notify the center coordinate of capture mark image through the image processing. Its measuring accuracy has been proved to be about $\pm$0.01mm through the repeated implementation over 200 times. This technique will shows the advantage of touch-indirect image capture idea using cone-shaped touch prove in various symmetrical shaped holes particulary, like tapped holes, chamfered holes, etc As a result, we attained our object in a view of the accuracy, economical efficiency, and functionality

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.8
• /
• pp.1029-1034
• /
• 2010

In this paper, we present the roundness profile and run-out error measurement for a rotating shaft. The devices for measuring the roundness require a precision rotation table which is used as a reference to obtain the circular profile. Therefore, the roundness measuring system is expensive and requires precision manufacturing. The two-point method for succession measurement has been used to obtain a linear profile or used in straightness measurement using two displacement measuring devices. In this paper, the method is used for measuring the circular profile of a rotating shaft. A method to remove the vibration of the shaft, i.e., the run-out, is used, and the original circular profile is obtained from the measured raw data that excludes the run-out error of the rotating shaft. This method will be useful for obtaining the precise circular profile without using a precision reference circular artifact.

• Journal of Biosystems Engineering
• /
• v.40 no.3
• /
• pp.165-177
• /
• 2015

Purpose: Accurate monitoring of soil strength is a key technology applicable to various precision agricultural practices. Soil strength has been traditionally measured using a cone penetrometer, which is time-consuming and expensive, making it difficult to obtain the spatial data required for precision agriculture. To improve the current, inefficient method of measuring soil strength, our objective was to develop and evaluate an in-situ system that could measure horizontal soil strength in real-time, while moving across a soil bin. Methods: Multiple cone-shape penetrometers were horizontally assembled at the front of a vertical plow blade at intervals of 5 cm. Each penetrometer was directly connected to a load cell, which measured loads of 0-2.54 kN. In order to process the digital signals from every individual transducer concurrently, a microcontroller was embedded into the measurement system. Wireless data communication was used between a data storage device and this real-time horizontal soil strength (RHSS) measurement system travelling at 0.5 m/s through an indoor experimental soil bin. The horizontal soil strength index (HSSI) measured by the developed system was compared with the cone index (CI) measured by a traditional cone penetrometer. Results: The coefficient of determination between the CI and the HSSI at depths of 5 cm and 10 cm ($r^2=0.67$ and 0.88, respectively) were relatively less than those measured below 20 cm ($r^2{\geq}0.93$). Additionally, the measured HSSIs were typically greater than the CIs for a given numbers of compactor operations. For an all-depth regression, the coefficient of determination was 0.94, with a RMSE of 0.23. Conclusions: A HSSI measurement system was evaluated in comparison with the conventional soil strength measurement system, CI. Further study is needed, in the form of field tests, on this real-time measurement and control system, which would be applied to precision agriculture.

• Journal of Biosystems Engineering
• /
• v.41 no.4
• /
• pp.304-312
• /
• 2016

Purpose: Soil strength has been measured using a cone penetrometer, which is making it difficult to obtain the spatial data required for precision agriculture. Our objectives were to evaluate real-time horizontal soil strength (RHSS) to measure soil strength in real time while moving across the field. Using the RHSS data, the tillage depth was determined, and the power consumption of a tractor and rotavators were compared. Methods: The horizontal soil-strength index (HSSI) obtained by the RHSS was compared with the cone index (CI), which was measured using a cone penetrometer. Comparison analysis in accordance with the measurement depth that increased at 5-cm interval was conducted using kriged maps at six sensing depths. For tillage control and evaluation of the power consumption, the system was installed with a potentiometer for tillage depth, a torque sensor from the rear axle, and a power take-off (PTO) shaft. Results: The HSSI was lower than the CI, but they were the same at 54.81% of the total grids for the 5-cm depth and at 3.85% for the 10-cm depth. In accordance with the recommended tillage map, tillage operations between 0 and 15 cm left 2.3% and 7% residue cover on the soil, and that between 20 and 10 cm covered a wider utilization of 3% and 18.4%, respectively. When the tillage depth was 15 cm, the comparison result of the power requirements between the PTO and rear axle in terms of control performance revealed that the maximum power requirements of the axle and PTO were 44.63 and 23.24 kW, respectively. Conclusions: An HSSI measurement system was evaluated by comparison with the conventional soil strength measurement system (CI) and applied to a tractor to compare the tillage power consumption. Further study is needed on its application to various farm works using a tractor for precision agriculture.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.2
• /
• pp.73-78
• /
• 2020

Musculoskeletal disease is often caused by sitting down for long period's time or by bad posture habits. In order to prevent musculoskeletal disease in daily life, it is the most important to correct the bad sitting posture to the right one through real-time monitoring. In this study, to detect the sitting information of user's without any constraints, we propose posture measurement system based on multi-channel pressure sensor and CNN model for classifying sitting posture types. The proposed CNN model can analyze 5 types of sitting postures based on sitting posture information. For the performance assessment of posture classification CNN model through field test, the accuracy, recall, precision, and F1 of the classification results were checked with 10 subjects. As the experiment results, 99.84% of accuracy, 99.6% of recall, 99.6% of precision, and 99.6% of F1 were verified.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.826-842
• /
• 2024

As 5G and AI continue to develop, there has been a significant surge in the healthcare industry. The COVID-19 pandemic has posed immense challenges to the global health system. This study proposes an FL-supported edge computing model based on federated learning (FL) for predicting clinical outcomes of COVID-19 patients during hospitalization. The model aims to address the challenges posed by the pandemic, such as the need for sophisticated predictive models, privacy concerns, and the non-IID nature of COVID-19 data. The model utilizes the FATE framework, known for its privacy-preserving technologies, to enhance predictive precision while ensuring data privacy and effectively managing data heterogeneity. The model's ability to generalize across diverse datasets and its adaptability in real-world clinical settings are highlighted by the use of SHAP values, which streamline the training process by identifying influential features, thus reducing computational overhead without compromising predictive precision. The study demonstrates that the proposed model achieves comparable precision to specific machine learning models when dataset sizes are identical and surpasses traditional models when larger training data volumes are employed. The model's performance is further improved when trained on datasets from diverse nodes, leading to superior generalization and overall performance, especially in scenarios with insufficient node features. The integration of FL with edge computing contributes significantly to the reliable prediction of COVID-19 patient outcomes with greater privacy. The research contributes to healthcare technology by providing a practical solution for early intervention and personalized treatment plans, leading to improved patient outcomes and efficient resource allocation during public health crises.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.12
• /
• pp.491-498
• /
• 2019

Digital twin is a technology that virtualizes physical objects of the real world on a computer. It is used by collecting sensor data through IoT, and using the collected data to connect physical objects and virtual objects in both directions. It has an advantage of minimizing risk by tuning an operation of virtual model through simulation and responding to varying environment by exploiting experiments in advance. Recently, artificial intelligence and machine learning technologies have been attracting attention, so that tendency to virtualize a behavior of physical objects, observe virtual models, and apply various scenarios is increasing. In particular, recognition of each robot's motion is needed to build digital twin for co-robot which is a heart of industry 4.0 factory automation. Compared with modeling based research for recognizing motion of co-robot, there are few attempts to predict motion based on sensor data. Therefore, in this paper, an experimental environment for collecting current and inertia data in co-robot to detect the motion of the robot is built, and a motion prediction model based on the collected sensor data is proposed. The proposed method classifies the co-robot's motion commands into 9 types based on joint position and uses current and inertial sensor values to predict them by accumulated learning. The data used for accumulating learning is the sensor values that are collected when the co-robot operates with margin in input parameters of the motion commands. Through this, the model is constructed to predict not only the nine movements along the same path but also the movements along the similar path. As a result of learning using SVM, the accuracy, precision, and recall factors of the model were evaluated as 97% on average.

• Korean Journal of Environment and Ecology
• /
• v.30 no.4
• /
• pp.793-799
• /
• 2016

This study examined Platanus orientalis and Ulmus davidiana planted in downtown parks to identify the correlations among microclimatic factors such as temperature in the crown, air flow, and wind speed. For the field survey, measurements were taken at 1 hour intervals from 09:00 am to 06:00 pm in August. For the measurement of microclimatic factors, data on temperature, light intensity, air flow, and wind speed were collected using a quantum sensor (PAR Quantum Sensor SKP215), a precision thermometer (Pt1000-Sensor), and a combination anemometer (1467 G4 & HG4). The results of the analysis demonstrated that both Platanus orientalis and Ulmus davidiana, showed a greater cooling effect inside the crown as compared with the outside temperature. The cooling effect inside the crown was more evident with air flow and wind speed factors. With relation to wind, the inner temperature of the crown of Platanus orientalis decreased due to air flow while that of Ulmus davidiana decreased due to wind speed. With no wind, the average variation in temperature inside the crown was $-0.9^{\circ}C$ for Ulmus davidiana and $-0.958^{\circ}C$ for Platanus orientalis, indicating that Platanus orientalis was relatively more effective in lowering the temperature of the planting space than Ulmus davidiana. This study is significant because it shows that different tree species have different effects on the microclimate and that factors affecting the formation of the microclimate of trees may vary with species. Further studies on species other than broad leaf trees, such as evergreen trees and shrubs, are required in order to plan the distribution of landscaping trees that are effective in regulating the microclimate within urban green spaces.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.1
• /
• pp.30-38
• /
• 2017

In this paper, we propose an underwater acoustic sensor fault detection method for passive sonar systems. In general, a passive sonar system displays processed results of array signals obtained from tens of the acoustic sensors as a two-dimensional image such as displays for broadband or narrowband analysis. Since detection result display in the operation software is to display the accumulated result through the array signal processing, it is difficult to determine the possibility where signal may be contaminated by the fault or failure of a single channel sensor. In this paper, accordingly, we propose a detection method based on the analysis of RMSCR (Root Mean Square Crossing-Rate), and the processing techniques for the faulty sensors are analyzed. In order to evaluate the performance of the proposed method, the precision of detecting fault sensors is measured by using signals acquired from real array being operated in several coastal areas. Besides, we compare performance of fault processing techniques. From the experiments, it is shown that the proposed method works well in underwater environments with high average RMS, and mute (set to zero) shows the best performance with regard to fault processing techniques.