Characterization of machining quality attributes based on spindle probe, coordinate measuring machine, and surface roughness data

Tseng, Tzu-Liang Bill,Kwon, Yongjin James Society for Computational Design and Engineering 2014 Journal of computational design and engineering Vol.1 No.2

This study investigates the effects of machining parameters as they relate to the quality characteristics of machined features. Two most important quality characteristics are set as the dimensional accuracy and the surface roughness. Before any newly acquired machine tool is put to use for production, it is important to test the machine in a systematic way to find out how different parameter settings affect machining quality. The empirical verification was made by conducting a Design of Experiment (DOE) with 3 levels and 3 factors on a state-of-the-art Cincinnati Hawk Arrow 750 Vertical Machining Center (VMC). Data analysis revealed that the significant factor was the Hardness of the material and the significant interaction effect was the Hardness + Feed for dimensional accuracy, while the significant factor was Speed for surface roughness. Since the equally important thing is the capability of the instruments from which the quality characteristics are being measured, a comparison was made between the VMC touch probe readings and the measurements from a Mi-tutoyo coordinate measuring machine (CMM) on bore diameters. A machine mounted touch probe has gained a wide acceptance in recent years, as it is more suitable for the modern manufacturing environment. The data vindicated that the VMC touch probe has the capability that is suitable for the production environment. The test results can be incorporated in the process plan to help maintain the machining quality in the subsequent runs.

인도네시아어 기계번역은 가능한가?

변윤행 한국아시아학회 2019 아시아연구 Vol.22 No.4

Many researches have been done on machine translation and a lot of significant research results have been produced. The whole premise of 'machine translation' here is English. If a certain level of Korean-English machine translation is possible, it is logical that machine translation in special foreign languages, including Indonesian, should also be possible. In fact, however, entering Korean-Indonesian, Indonesian-Korean into machine translation programs such as Google Translate and Naver Papago and Kakao often results in translation that differs from the quality level of Korean-English machine translation. In this regards, this study attempts to examine the translation status and translation quality of Google Trans and Naver Papago, Kakao's Korean-Indonesian, and Indonesian-Korean, then compare the above translation quality with the Korean-English-Indonesian translation quality. For comparison, the Korean text will be set from non-literary text, which is less likely to cause errors, and will compare the translation quality of Korean-Indonesian, Indonesian-Korean and translation quality when English is set as an intermediate language. Finally, this research discusses the way to improve the translation quality by deducing the reasons for the difference in translation quality, and predicts the prospects for Korean-Indonesian, Indonesian-Korean machine translation. 기계번역의 품질이 급격하게 향상되면서 번역 분야에서도 기계가 곧 인간을 대체할 수 있게 될 것이라는 전망이 힘을 얻고 있다. 일정 수준의 영어-한국어 기계번역이 가능하다면, 인도네시아어를 포함한 특수외국어의 기계번역도 가능해야 하는 것이 논리적으로 타당하다. 그러나 실제로 국내에서 사용하는 기계번역 프로그램인 구글 트랜스와 네이버 파파고, 카카오 번역 프로그램에 한국어-인도네시아어, 인도네시아어-한국어를 입력하면 영어-한국어, 한국어-영어 기계번역의 품질 수준과 다른 번역결과가 나오는 경우가 더 많다. 그 이유는 무엇일까. 그리고 인도네시아어 같은 특수외국어는 기계번역이 불가능한 것일까. 본 연구에서는 기계번역 프로그램의 한국어-인도네시아어, 인도네시아어-한국어의 번역 상황과 번역품질을 살펴보고, 위 번역품질을 한국어-영어-인도네시아어, 인도네시아어-영어-한국어 번역품질과 비교하여 번역품질이 차이가 나는 이유를 추론하고 있다. 또한 최근 번역품질 향상의 방법으로 사용되는 크라우드소싱에서 나타날 수 있는 문제점을 살펴보고 그 해결 방안을 모색하여 한국어-인도네시아어, 인도네시아어-한국어 기계번역의 전망을 예측해 본다.

590 MPa급 고강도강과 6xxx계 알루미늄 합금의 Flow Drilling Screw 접합품질 예측 알고리즘 개발

최유리,김동윤,장준명,유지영,이승환 대한용접접합학회 2024 대한용접·접합학회지 Vol.42 No.4

Flow drilling screw (FDS) process is applied to various components such as car bodies and battery cases due to its advantage of enabling one-sided joining. Various studies have been conducted on the correlation between monitored process parameters and joint quality. These correlations suggest the potential for non-destructive classification or prediction of joint quality using process monitoring signals. In this study, the effect of FDS process parameters on joint quality was analyzed, and a decision tree-based quality prediction model for classifying joint quality was developed. The material combination consisted of a 1.8 mm thick SGAFC 590DP as the upper plate and a 3.0 mm thick Al 6061 as the lower plate. To develop the joint quality prediction algorithm, the effect of process parameters in each process step on joint quality was analyzed. It is used as input data to identify various features. The output data were generated by classifying the products into three categories from class 0 to class 2. Based on the extracted feature data, a machine learning algorithm was trained to develop the joint quality prediction model.

머신러닝을 활용한 사출성형 품질 예측에 관한 연구

김대호,홍준희 한국생산제조학회 2022 한국생산제조학회지 Vol.31 No.4

The injection molding process is a process in which products, such as plastics and rubber, are mass-produced. It is essential in industry, from high-tech industries such as automobiles and aerospace parts, to daily necessities. The quality control of injection molding is based on the operator's experience or involves measurements and evaluations of some first products; hence, real-time process monitoring and data-based quality control are required. In this study, an autoencoder and a support vector machine were used to predict quality, and the learning dataset was collected using a sensor attached to the injection molding machine. Next, good and bad products were labeled, and hyperparameters were changed for each model. By learning, the performance of each model was evaluated. Reliability improvement is expected through data-based quality management using the machine learning model proposed in this study to predict the quality based on changes under process conditions.

머신러닝 자동화 알고리즘을 이용한 수질예측 모형 구축

박정수 대한상하수도학회 2022 상하수도학회지 Vol.36 No.6

The management of algal bloom is essential for the proper management of water supply systems and to maintain the safety of drinking water. Chlorophyll-a(Chl-a) is a commonly used indicator to represent the algal concentration. In recent years, advanced machine learning models have been increasingly used to predict Chl-a in freshwater systems. Machine learning models show good performance in various fields, while the process of model development requires considerable labor and time by experts. Automated machine learning(auto ML) is an emerging field of machine learning study. Auto ML is used to develop machine learning models while minimizing the time and labor required in the model development process. This study developed an auto ML to predict Chl-a using auto sklearn, one of most widely used open source auto ML algorithms. The model performance was compared with other two popular ensemble machine learning models, random forest(RF) and XGBoost(XGB). The model performance was evaluated using three indices, root mean squared error, root mean squared error-observation standard deviation ratio(RSR) and Nash-Sutcliffe coefficient of efficiency. The RSR of auto ML, RF, and XGB were 0.659, 0.684 and 0.638, respectively. The results shows that auto ML outperforms RF, and XGB shows better prediction performance than auto ML, while the differences between model performances were not significant. Shapley value analysis, an explainable machine learning algorithm, was used to provide quantitative interpretation about the model prediction of auto ML developed in this study. The results of this study present the possible applicability of auto ML for the prediction of water quality.

GOCI 위성영상과 기계학습을 이용한 한반도 연안 수질평가지수 추정

장은나 ( Eunna Jang ),임정호 ( Jungho Im ),하성현 ( Sunghyun Ha ),이상균 ( Sanggyun Lee ),박영규 ( Young Gyu Park ) 대한원격탐사학회 2016 大韓遠隔探査學會誌 Vol.32 No.3

우리나라는 대규모 산업단지와 대도시들이 연안에 집중되면서 연안의 오염이 날로 심각해지고 있다. 이러한 연안 오염을 모니터링하기 위해서 위성 영상을 이용한 연안 수질평가지수 모니터링 연구가 수행 될 필요가 있다. 수질평가지수란 저층 산소포화도, 엽록소 농도, 투명도, 용존무기질소 및 용존무기인 농도를 수질평가 항목으로 구성하여 해양환경관리법에 따른 해양환경기준을 통해 해역별로 기준을 설정하여 산출하는 지수이다. 이 연구는 한반도 주변의 연안지역을 대상으로 2011년부터 2013년까지의 현장관측 자료 및 Geostationary Ocean Color Imager (GOCI) 위성 영상을 이용하여 연안 표층 해수에 대한 기계학습 기반의 두 가지 수질평가지수 추정 기법을 개발하였다. 첫 번째 방법으로는 GOCI 반사도를 이용하여 추정된 수질평가 항목들로 수질평가지수를 계산하였고, 두 번째 방법은 GOCI 반사도 및 산출물(엽록소 농도, 총 부유물질, 용존유기물)을 이용하여 수질평가지수를 추정하였다. 기계학습으로는 Random Forest(RF), Support Vector Regression (SVR), Cubist를 사용하였다. 수질평가 항목 추정에서 투명도의 정확도가 가장 높게 나타났으며, 모든 수질평가 항목 추정에서 세 가지 기계학습 중 RF의 정확도가 가장 높았다. 하지만 추정된 수질평가 항목들로 계산한 수질평가지수는 추정된 수질평가 항목들의 오차와 저층 산소포화도의 불확실성으로 인해 정확도가 높지는 않았다. 반면 GOCI 반사도와 산출물을 이용하여 추정한 수질평가지수는 현장 관측 기반 수질평가지수와 비교했을 때 첫 번째 방법보다 정확도가 높게 나타났다. 또한 엽록소 농도가 수질평가지수 추정에 가장 중요한 변수로 나타났다. In Korea, most industrial parks and major cities are located in coastal areas, which results in serious environmental problems in both coastal land and ocean. In order to effectively manage such problems especially in coastal ocean, water quality should be monitored. As there are many factors that influence water quality, the Korean Government proposed an integrated Water Quality Index (WQI) based on in situmeasurements of ocean parameters(bottom dissolved oxygen, chlorophyll-a concentration, secchi disk depth, dissolved inorganic nitrogen, and dissolved inorganic phosphorus) by ocean division identified based on their ecological characteristics. Field-measured WQI, however, does not provide spatial continuity over vast areas. Satellite remote sensing can be an alternative for identifying WQI for surface water. In this study, two schemes were examined to estimate coastal WQI around Korea peninsula using in situ measurements data and Geostationary Ocean Color Imager (GOCI) satellite imagery from 2011 to 2013 based on machine learning approaches. Scheme 1 calculates WQI using estimated water quality-related factors using GOCI reflectance data, and scheme 2 estimates WQI using GOCI band reflectance data and basic products(chlorophyll-a, suspended sediment, colored dissolved organic matter). Three machine learning approaches including Random Forest (RF), Support Vector Regression (SVR), and a modified regression tree(Cubist) were used. Results show that estimation of secchi disk depth produced the highest accuracy among the ocean parameters, and RF performed best regardless of water quality-related factors. However, the accuracy of WQI from scheme 1 was lower than that from scheme 2 due to the estimation errors inherent from water quality-related factors and the uncertainty of bottom dissolved oxygen. In overall, scheme 2 appears more appropriate for estimating WQI for surface water in coastal areas and chlorophyll-a concentration was identified the most contributing factor to the estimation of WQI.

ESTIMATION OF RIDE QUALITY OF A PASSENGER CAR WITH NONLINEAR SUSPENSION

S. J. CHO,Y. S. CHOI 한국자동차공학회 2007 International journal of automotive technology Vol.8 No.1

The nonlinear characteristics of a suspension is directly related to the ride quality of a passenger car. In this study, the nonlinear characteristics of a spring and a damper of a passenger car is analyzed by dynamic experiments using the MTS single-axial testing machine. Also, a mathematical nonlinear dynamic model for the suspension is devised to estimate the ride quality using the K factor. And the effect on the variation of the parameters of the suspension is examined. The results showed that the dynamic viscosity of the oil in a damper was the parameter that most influeced the ride quality of a passenger car for the ride quality of a passenger car.

Prediction of Soil Quality in Rwanda for Ideal Cultivation of Potato (Solanum tuberosum) Using Fuzzy Logic and Machine Learning

Christine Musanase,Anthony Vodacek,Damien Hanyurwimfura,Alfred Uwitonze,Aloys Fashaho,Adrien Turamyemyirijuru 한국지능시스템학회 2023 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.23 No.2

The ability to estimate soil quality has great value for agriculture, especially for low-incomeregions with minimal agricultural and financial resources. This prediction provides users withinformation that is useful in determining whether the soil is suitable for a specific crop, such aspotato (Solanum tuberosum). Farmers in Rwanda lack information on soil quality. There arenot enough soil laboratories to perform the requisite measurements of NPK, pH, and organiccarbon, nor are there enough experts to analyze the data and provide farmers with timelyresults. The prime objective of the proposed study is to develop a predictive framework thatcan estimate soil quality for the ideal cultivation of potato (Solanum tuberosum) considering acase study of Rwanda. In this study, bootstrapping is used to augment the small soil dataset,and fuzzy logic is used to label soil data into four classes of soil suitability, with verification ofthe labeling by soil experts. Several machine learning methods are then tested on the labeleddata, resulting in the classification of suitability for the augmented dataset and an assessment oftheir performance as a way to support experts in predicting soil quality. All machine learningmethods applied were viable, with the best performance achieved using an artificial neuralnetwork. The quantified outcome showed that the adoption of a neural-network-based schemehas an average accuracy of 32% in contrast to other learning schemes. However, 70%-80%accuracy was achieved upon the adoption of fuzzy logic.

Comparative Evaluation of Attribute-Enabled Supervised Classification in Predicting the Air Quality

P. Subbulakshmi,S. Vimal,Y. Harold Robinson,Amit Verma,Janmenjoy Nayak 대한공간정보학회 2023 Spatial Information Research Vol.31 No.4

Air pollution demonstrates the appearance of toxins into the air which is blocking human prosperity and the earth. It will portray as potentially the riskiest threats that humanity anytime faced. It makes hurt animals, harvests to thwart these issues in transportation territories need to expect air quality from pollutions utilizing AI systems and IoT. Along these lines, air quality evaluation and assumption has become a huge target for human health factors and also affect internal organs related to respiratory. The accuracy of Air Pollution prediction has been involved with the machine learning techniques and the best accuracy model is identified. The air quality prediction dataset is used for identifying the meteorology air pollution data while the predicted model is involved the decision tree computation for predicting the toxin contents in the region, the Air quality indicator is used to assess the pollution level and monitoring the air quality. The performance analysis shows that the decision tree technique has produced the better results in the performance metrics of Accuracy, precision, recall, and F1-score with the minimized error values while the comparative evaluation of Attribute-enabled classification has identified the best technique for predicting the air quality.

신경망 기계번역의 작동 원리와 번역의 정확률

강병규(Kang, Byeong-kwu),이지은(Lee, Ji-eun) 한국중어중문학회 2018 中語中文學 Vol.- No.73

In this paper, we examined the mechanism of operation of the neural network model(NMT), which is attracting attention in the field of machine translation research. The NMT model consists of a process in which the computer reads the original text in sentence units and then generates the optimal translation corresponding to the sentence using the parameters obtained by deep learning. In the process of finding the optimal translation there is no need to construct separate translation dictionaries or translation patterns because the computer will learn on its own with parallel corpus. The NMT model is simpler and more general than the existing models. For the quality of neural network machine translation, research has been conducted mainly on English. However, the research on the translation quality of non-English languages has received relatively little attention. Especially, it is not an exaggeration to say that the study on Chinese - Korean NMT quality has not yet been successful. In this paper, we analyzed how accurately the NMT translates Chinese - Korean sentences. The programs used to evaluate the accuracy of translation are GNMT, N2MT, Baidu NMT. For the translation evaluation, we selected 370 sentences from Chinese textbooks, academic papers, newspapers, TV scripts. And the machine translation results were evaluated in terms of word translation, phrase translation, and sentence translation. According to the result of the evaluation, the accuracy of N2MT and Baidu NMT is higer than that of GNMT for the basic colloquial expressions. However, in translating practical sentences such as newspaper reports, product manuals, web documents, business expressions, and TV conversations, the accuracy of GNMT and N2MT was higher than that of Baidu NMT. In this paper, we also discussed how to use the NMT effectively. It is true that the NMT model has improved the translation quality. However, it still does not produce very high quality translations for the source texts. It will not be easy for machine translation to completely replace human translation in the future. But machine translation programs can be an excellent aid to human translation. The NMT model learns the translation data on its own and can predict the optimal translation. Therefore, if the NMT model is specialized for the purpose of the translator, it can be used as a convenient translation tool. Developing a translation model based on the neural network theory will contribute to enhancing the accuracy and efficiency of the translation.