• 산업경영시스템학회지
• /
• 제43권1호
• /
• pp.123-131
• /
• 2020

There have been a lot of studies in the past for the method of predicting the failure of a machine, and recently, a lot of researches and applications have been generated to diagnose the physical condition of the machine and the parts and to calculate the remaining life through various methods. Survival models are also used to predict plant failures based on past anomaly cycles. In particular, special machine that reflect the fluid flow and process characteristics of chemical plants are connected to hundreds or thousands of sensors, so there are not many factors that need to be considered, such as process and material data as well as application of derivative variables. In this paper, the data were preprocessed through time series anomaly detection based on unsupervised learning to predict the abnormalities of these special machine. Next, clustering results reflecting clustering-based data characteristics were applied to produce additional variables, and a learning data set was created based on the history of past facility abnormalities. Finally, the prediction methodology based on the supervised learning algorithm was applied, and the model update was confirmed to improve the accuracy of the prediction of facility failure. Through this, it is expected to improve the efficiency of facility operation by flexibly replacing the maintenance time and parts supply and demand by predicting abnormalities of machine and extracting key factors.

• 대한조선학회논문집
• /
• 제59권4호
• /
• pp.243-250
• /
• 2022

In the design stage of hull forms, a fast prediction method of resistance performance is needed. In these days, large test matrix of candidate hull forms is tested using Computational Fluid Dynamics (CFD) in order to choose the best hull form before the model test. This process requires large computing times and resources. If there is a fast and reliable prediction method for hull form performance, it can be used as the first filter before applying CFD. In this paper, we suggest the offset-based performance prediction method. The hull form geometry information is applied in the form of 2D offset (non-dimensionalized by breadth and draft), and it is studied using Convolutional Neural Network (CNN) and adapted to the model test results (Residual Resistance Coefficient; C_R). Some additional variables which are not included in the offset data such as main dimensions are merged with the offset data in the process. The present model shows better performance comparing with the simple regression models.

• Structural Engineering and Mechanics
• /
• 제82권4호
• /
• pp.445-458
• /
• 2022

Some of the control systems used in engineering structures that use sensors and decision systems have some time delay reducing efficiency of the control system or even might make it unstable. In this research, in addition to considering the effect of the time delay in vibration control process, predictive control is used to compensate the time delay. A semi-active vibration control approach with the help of magneto-rheological dampers is implemented. In addition to using fuzzy inference system to determine the appropriate control voltage for MR damper, structural behavior prediction system and specifying future responses are also used such that the time delays occurring within control process are overcome. For this purpose, determination of prediction horizon is conducted for one, five, and ten steps ahead for single degree of freedom structures with periods ranging from 0.1 to 4 seconds, subjected to twenty earthquake excitations. The amount of time delay applied to the control system is 0.1 seconds. The obtained results indicate that for 0.1 second time delay, average prediction error values compared to the case without time delay is 3.47 percent. Having 0.1 second time delay in a semi-active control system reduces its efficiency by 11.46 percent; while after providing the control system with structure behavior prediction, the difference in the results for the control system without time delay is just 1.35 percent on average; indicating a 10.11 percent performance improvement for the control system.

• 한국기계가공학회지
• /
• 제19권6호
• /
• pp.73-79
• /
• 2020

Although engineering plastics that are light-weight and have excellent mechanical performance have been widely applied in various industries in place of steel structures to reduce the burden of cost and time, there have been few studies related to their surface roughness. This study aims to evaluate the optimal effects of feed rate, cutting speed, and depth of cut as cutting parameters as well as nose angle on the surface characteristics of MC nylon in CNC lathe machining. To determine the best conditions under different nose radii, the experiments were performed based on the Taguchi L9(34) orthogonal array method, in which the resulting data was analyzed using the S/N ratio and ANOVA. Results indicate that the most significant contribution was feed rate followed by nose angle and cutting speed, whereas the depth of cut did not influence the performance. This study demonstrates that the suggested method for improving the surface finishing of MC nylon is efficient compared with results obtained from experimentation and prediction.

• 한국가스학회지
• /
• 제10권4호
• /
• pp.29-33
• /
• 2006

화학공정 설계에서 공정의 위험성 판단은 중요한 부분이다. 실제 화학공정에 사용되는 가연성 물질의 화재 및 폭발 위험성을 판단하는 인화점에 대한 예측은 그 방법 중의 하나이다. 본 연구에서는 2성분계 가연성 물질의 인화점에 대한 실험 자료를 이용하여 다변량 통계 분석법(partial least squares(PLS), quadratic partial least squares(QPLS))을 이용하여 2성분계 혼합물의 인화점을 예측하였고, 기존의 Raoult의 법칙과 Van Laar 식에 의한 예측값과 비교해 보았다.

• Korea-Australia Rheology Journal
• /
• 제16권4호
• /
• pp.163-168
• /
• 2004

In this study, an ultrasonic technique was employed to obtain pressure-volume-temperature (PVT) rela­tionship of polymer melt by measuring ultrasonic velocities under various temperatures and pressures. The proposed technique was applied to on-line monitoring of injection molding process as an attempt to predict quality of molded parts. From the comparison based on Tait equation, it was confirmed that the PVT behav­ior of a polymer is well described by the variation of ultrasonic velocities measured within the polymer medium. In addition, the changes in part weight and moduli were successfully predicted by combining the data collected from ultrasonic technique and artificial neural network algorithm. The results found from this study suggest that the proposed technique can be effectively utilized to monitor the evolution of solid­ification within the mold by measuring ultrasonic responses of various polymers during injection molding process. Such data are expected to provide a critical basis for the accurate prediction of final performance of molded parts.

• 소성∙가공
• /
• 제14권6호
• /
• pp.527-532
• /
• 2005

Among the failure modes which can occur in tube hydroforming such as wrinkling, bursting or buckling, the bursting by local instability under excessive tensile stresses is irrecoverable phenomenon. Thus, the accurate prediction of bursting condition plays an important role in producing the successfully hydroformed part without any defects. As the classical forming limit criteria, strain-based forming limit diagram (FLD) has widely used to predict the failure in sheet metal forming. However, it is known that the FLD is extremely dependant on strain path throughout the forming process. Furthermore, The application of FLD to hydroforming process, where strain path is no longer linear throughout forming process, may lead to misunderstanding for fracture initiation. In this work, stress-based forming limit diagram (FLSD), which is strain path-independent and more general, was applied to prediction of forming limit in tube hydroforming. Combined with the analytical FLSD determined from plastic instability theory, finite element analyses were carried out to find out the state of stresses during hydroforming operation, and then FLSD is utilized as forming limit criterion. In addition, the approach is verified by a series of bulge tests in view of bursting pressure and shows a good agreement. Consequently, it is shown that the approach proposed in this paper will provide a feasible method to satisfy the increasing practical demands for judging the forming severity in hydroforming processes.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2005년도 춘계학술대회 논문집
• /
• pp.92-96
• /
• 2005

Among the failure modes which can be occurred in tube hydroforming such as wrinkling, bursting or buckling, the bursting by local instability under excessive tensile stresses is irrecoverable phenomenon. Thus, the accurate prediction of bursting condition plays an important role in producing the successfully hydroformed part without any defects. As the classical forming limit criteria, strain-based forming limit diagram has widely used to predict the failure in sheet metal forming. However, it is known that the FLD is extremely dependant on strain path throughout the forming process. Furthermore, the path-dependent limitation of FLD makes the application to hydroforming process, where strain path is no longer linear throughout forming process, more careful. In this work, stress-based forming limit diagram (FLSD), which is strain path-independent and more general, was applied to prediction of forming limit in tube hydroforming. Combined with the analytical FLSD determined from plastic instability theory, finite element analyses were carried out to find out Ihe state of stresses during hydroforming operation, and then FLSD is utilized as forming limit criterion. In addition, the approach is verified with a series of bulge tests in view of bursting pressure and shows a good agreement. Consequently, it is shown that the approach proposed in this paper will provide a feasible method to satisfy the increasing practical demands for judging the farming severity in hydroforming processes.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 추계학술대회 논문집
• /
• pp.604-607
• /
• 2005

In the electro-discharge machining the machining performance is closely related to the characteristics of discharge which can be identified from electrical behavior in gap between workpiece and electrode. Therefore, the accurate prediction of electrical behavior in electro-discharge machining (EDM) is useful to process control and optimization. However, any simulation model fur prediction of electrical behavior in EDM process has never been reported until now. In this study, a simulation model is developed to analyze the electrical behavior of electro-discharge plasma which significantly influences electrical behavior in EDM process. For the purpose of this the fundamentals of electro-discharge mechanism such as inception, propagation, formation of plasma channel and termination are investigated to accurately predict the cycle of discharge plasma in EDM. As a result, a mathematical model of electro-discharge plasma is constructed with considering the fundamentals of electro-discharge plasma. Consequently, it is demonstrated that the developed model can predict the electrical behavior of plasma such as electron density in various conditions.

• 한국기계가공학회지
• /
• 제20권4호
• /
• pp.119-126
• /
• 2021

During the development of a weapon system, the concept of maintainability is used for quantitatively predicting and analyzing the maintenance time. However, owing to the complexity of a weapon system, the standard maintenance time predicted during the system's development differs significantly from the measured time during the operation of the equipment after the system's development. According to the analysis presented in this paper, the maintenance time can be predicted by considering the system's complexity on the basis of the military specifications, and the procedure can be Part B of Procedure II and Method B of Procedure V. The maintenance work elements affected by the system complexity were identified by the analytic hierarchy process technique, and the system-complexity-reflecting weights of the maintenance work elements were calculated by the Delphi method, which involves expert surveys. Based on MIL-HDBK-470A and MIL-HDBK-472, it is going to present a Korean-style maintainability prediction method that reflects system complexity of weapons systems.