자기상관이 있는 장치산업에서 공정 진단 및 부적합품률 제어모형에 관한 연구

구자활,김대현,조진형 한국산업경영시스템학회 2009 한국산업경영시스템학회 학술대회 Vol.2009 No.춘계

Control chart is one of the most well-known tools used to monitor and control the process in real time. However, application of the chart is predicated on the assumption that each observed data has no correlation with one another. In recent years, manufacturing process has been automated and on-line monitor has become possible. They are widely used in chemical industry or instrumental process, where sensors monitor tanks, furnace, and flow of raw materials. In this kind of process, sampling interval for data collection tends to be short compared with the overall processing time, resulting in significant autocorrelation among data. The existence of the autocorrelation violates the premise of iid for the traditional control chart, whose application to such a case could lead to the wrong conclusion. The effect of autocorrelation can be understood employing a different statistical model, and it will provide the way to determine if the process is control-in or control-out. The best available model for analyzing time-series data with autocorrelation is ARMIA(autoregressive integrated moving average.) However, if manufacturing process itself is rather large in scale, and measuring physical properties, difficult, and there are large number of variables to be controlled, it is quite complicated to not only make diagnosis and control the process but also determine the relationship between control variables and occurrences of non-conforming products. These control variables tend to be interrelated. It is necessary to find out critical factors and realize effective process control by controlling those factors. In this study, we present a control model based on time series data with autocorrelation in instrumental process, and show how to effectively deal with non-conforming products, by applying it to data from real process.

Economic performance of an EWMA chart for monitoring MMSE-controlled processes

이재헌,양완연 한국데이터정보과학회 2004 한국데이터정보과학회지 Vol.15 No.2

Statistical process control(SPC) and engineering process control(EPC) are two complementary strategies for quality improvement. An integrated process control(IPC) can use EPC to reduce the effect of predictable quality variations and SPC to monitor the process for detection of special causes. In this paper we assume an IMA(1,1) model as a disturbance process and an occurrence of a level shift in the process, and we consider the economic performance for applying an EWMA chart to monitor MMSE-controlled processes. The numerical results suggest that the IPC scheme in an IMA(1,1) disturbance model does not give additional advantages in the economic aspect.

Performance Evaluation of Multivariate SPC for Monitoring Batch Processes

Young-il Kim 전북대학교 산업경제연구소 2014 아태경상저널 Vol.6 No.2

Based on batch processes data obtained from a chemical company, the performances of the Hotelling’s T2 control chart and the Squared Prediction Error (SPE) control chart built by multi-way principal component analysis are evaluated for monitoring batch processes. Thirteen in-control batch processes lasting two hours are used as reference information to build T2 and SPE control charts. A total of twenty batch processes (ten as out-of-control batch processes and another set of ten for in-control batch processes) are projected in both control charts. Performances of both control charts are measured by estimating empirical statistical power of detecting out-of-control signals and Type I error (False alarm) rates at each time period and overall. By comparing the performance of two control charts on theaspects of estimated power and false alarm rate, the T2 control chart is recommended for monitoring the batch processes considered.

통합공정관리에서 출력변수와 입력변수를 탐지하는 절차의 비교

이재헌 한국데이터정보과학회 2011 한국데이터정보과학회지 Vol.22 No.4

Two widely used approaches for improving the quality of the output of a process are statistical process control (SPC) and automatic process control (APC). In recent hybrid processes that combine aspects of the process and parts industries, process variations due to both the inherent wandering and special causes occur commonly, and thus simultaneous application of APC and SPC schemes is needed to effectively keep such processes close to target. The simultaneous implementation of APC and SPC schemes is called integrated process control (IPC). In the IPC procedure, the output variables are monitored during the process where adjustments are repeatedly done by its controller. For monitoring the APC-controlled process, control charts can be generally applied to the output variable. However, as an alternative, some authors suggested that monitoring the input variable may improve the chance of detection. In this paper, we evaluate the performance of several monitoring statistics, such as the output variable, the input variable, and the difference variable, for efficiently monitoring the APC-controlled process when we assume IMA(1,1) noise model with a minimum mean squared error adjustment policy. 통계적 공정관리 (statistical process control; SPC)와 자동공정관리 (automatic process control; APC)는 공정의 품질을 향상시키기 위하여 가장 널리 사용하는 방법이다. 이 두 종류의 관리절차는 서로 독립적으로 적용되고 연구되어져 왔지만, 현대의 생산 공정은 공정 자체가 복잡하고 혼합된 양상을 나타내기 때문에 두 관리절차를 병행하여 사용함으로써 관리효과를 증대시킬 수 있게 된다. 이와 같이 수정과 탐지를 동시에 사용하여 공정을 좀 더 효율적으로 관리하고자 하는 절차를 통합공정관리 (integrated process control; IPC)라고 한다. IPC의 기본절차는 잡음이 내재하는 공정에 대하여 수정조치를 취하고, 이러한 수정활동 중 공정에 이상원인이 발생했는지 관리도를 통하여 이를 탐지하는 것이다. APC로 조정된 공정을 관리할 경우 일반적으로 출력변수를 관리통계량으로 사용하고 있으나, 입력변수를 관리통계량으로 사용하는 연구 결과들도 있다. 이 논문에서는 누적이동평균(integrated moving average; IMA) (1,1) 잡음모형과 최소평균제곱오차 (minimum mean square error; MMSE) 수정을 가정할 경우, 출력변수, 입력변수, 그리고 출력변수와 입력변수의 정보를 모두 이용하는, 즉 출력과 입력변수의 차이변수를 사용하는 절차의 효율을 비교하고 있다.

Performance assessment of cascade controllers for nitrate control in a wastewater treatment process

류홍빈,유창규 한국화학공학회 2011 Korean Journal of Chemical Engineering Vol.28 No.3

A cascade control strategy is proposed to the benchmark simulation model 1 (BSM1) to enhance the treatment performance of nitrogen removal in a biological wastewater treatment plant. The proposed control approach consists of two control loops, a primary outer loop and a secondary inner loop. The method has two controllers of which the primary loop has a model predictive control (MPC) controller and the secondary loop has a proportional-integralderivative (PID) controller, which is a cascade MPC_PID controller. The primary MPC controller is to control the nitrate concentration in the effluent, and the secondary PID controller is to control the nitrate concentration in the final anoxic compartment. The proposed method controls the nitrate concentrations in the effluent as well as in the final anoxic reactor simultaneously to strictly satisfy the quality of the effluent as well as to remove the effects of disturbances more quickly by manipulating the external carbon dosage rate. Because the control performance assessment (CPA) technique has the features of determining the capability of the current controller and locating the best achievable performance,the other novelty of this paper is to suggest a relative closed-loop potential index (RCPI) which updates the CPA technology into a closed-loop cascade controller. The proposed method is compared with a cascade PID-PID control strategy and the original PID controller in BSM1 and an improved performance of the suggested cascade MPC-PID controller is obtained by using the CPA approach.

Performance Assessment of Cascade Control Strategy in Wastewater Treatment Process

Hongbin Liu,MinJung Kim,JungJin Lim,ChangKyoo Yoo 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10

As the public awareness of environmental protection increases and the environmental regulations become more stringent, effective control of the wastewater treatment process (WWTP) has become a research hotspot. In this paper, a cascade MPC and PID control strategy is introduced to the Benchmark Simulation Model 1 (BSM1). The proposed cascade control structure is composed of a primary MPC controller to control the nitrate concentration in the effluent and a secondary PID controller to control the nitrate concentration in the final anoxic compartment. The suggested method controls the nitrate concentrations in the effluent as well as in the final anoxic reactor simultaneously to strictly satisfy the quality of the effluent as well as to remove the effects of disturbances more quickly by manipulating the external carbon dosage. Because the control performance assessment (CPA) technique has the features of determining the capability of the current controller and locating the best achievable performance, the other novelty of this paper is to take the CPA technology into the wastewater treatment process. The CPA results indicate that the primary MPC controller has more potential to improve compared with the secondary PID controller.

통계적 품질관리를 위한 왜도의 활용

김훈태,임성욱 한국품질경영학회 2023 품질경영학회지 Vol.51 No.4

Purpose: Skewness is an indicator used to measure the asymmetry of data distribution. In the past, product quality was judged only by mean and variance, but in modern management and manufacturing environments, various factors and volatility must be considered. Therefore, skewness helps accurately understand the shape of data distribution and identify outliers or problems, and skewness can be utilized from this new perspective. Therefore, we would like to propose a statistical quality control method using skewness. Methods: In order to generate data with the same mean and variance but different skewness, data was generated using normal distribution and gamma distribution. Using Minitab 18, we created 20 sets of 1,000 random data of normal distribution and gamma distribution. Using this data, it was proven that the process state can be sensitively identified by using skewness. Results: As a result of the analysis of this study, if the skewness is within ± 0.2, there is no difference in judgment from management based on the probability of errors that can be made in the management state as discussed in quality control. However, if the skewness exceeds ±0.2, the control chart considering only the standard deviation determines that it is in control, but it can be seen that the data is out of control. Conclusion: By using skewness in process management, the ability to evaluate data quality is improved and the ability to detect abnormal signals is excellent. By using this, process improvement and process non-substitutability issues can be quickly identified and improved. Purpose: Skewness is an indicator used to measure the asymmetry of data distribution. In the past, product quality was judged only by mean and variance, but in modern management and manufacturing environments, various factors and volatility must be considered. Therefore, skewness helps accurately understand the shape of data distribution and identify outliers or problems, and skewness can be utilized from this new perspective. Therefore, we would like to propose a statistical quality control method using skewness. Methods: In order to generate data with the same mean and variance but different skewness, data was generated using normal distribution and gamma distribution. Using Minitab 18, we created 20 sets of 1,000 random data of normal distribution and gamma distribution. Using this data, it was proven that the process state can be sensitively identified by using skewness. Results: As a result of the analysis of this study, if the skewness is within ± 0.2, there is no difference in judgment from management based on the probability of errors that can be made in the management state as discussed in quality control. However, if the skewness exceeds ±0.2, the control chart considering only the standard deviation determines that it is in control, but it can be seen that the data is out of control. Conclusion: By using skewness in process management, the ability to evaluate data quality is improved and the ability to detect abnormal signals is excellent. By using this, process improvement and process non-substitutability issues can be quickly identified and improved.

GAUSSIAN PROCESS REGRESSION FEEDFORWARD CONTROLLER FOR DIESEL ENGINE AIRPATH

Volkan Aran,Mustafa Unel 한국자동차공학회 2018 International journal of automotive technology Vol.19 No.4

Gaussian Process Regression (GPR) provides emerging modeling opportunities for diesel engine control. Recent serial production hardwares increase online calculation capabilities of the engine control units. This paper presents a GPR modeling for feedforward part of the diesel engine airpath controller. A variable geotmetry turbine (VGT) and an exhaust gas recirculation (EGR) valve outer loop controllers are developed. The GPR feedforward models are trained with a series of mapping data with physically related inputs instead of speed and torque utilized in conventional control schemes. A physical model-free and calibratable controller structure is proposed for hardware flexibility. Furthermore, a discrete time sliding mode controller (SMC) is utilized as a feedback controller. Feedforward modeling and the subsequent airpath controller (SMC+GPR) are implemented on the physical diesel engine model and the performance of the proposed controller is compared with a conventional PID controller with table based feedforward.

정압제어를 위한 동적모델 해석 및 최적 퍼지 PID 제어기설계

오성권(Sung-Kwun Oh),조세희(Se-Hee Cho),이승주(Seung-Joo Lee) 대한전기학회 2012 전기학회논문지 Vol.61 No.2

In this study, we introduce a dynamic process model as well as the design methodology of optimized fuzzy controller for its efficient application to vacuum production system to produce a semiconductor, solar module and display and so on. In a vacuum control field, PID control method is widely used from the viewpoint of simple structure and preferred performance. But, PID control method is very sensitive to the change of environment of control system as well as the change of control parameters. Therefore, it’s difficult to get a preferred performance results from target system which has a complicated structure and lots of nonlinear factors. To solve such problem, we propose the design methodology of an optimized fuzzy PID controller through a following series of steps. First a dynamic characteristic of the target system is analyzed through a series of experiments. Second the process model is built up and its characteristic is compared with real process. Third, the optimized fuzzy PID controller is designed using genetic algorithms. Finally, the fuzzy controller is applied to target system and then its performance is compared with that of other conventional controllers(PID, PI, and Fuzzy PI controller). The performance of the proposed fuzzy controller is evaluated in terms of auto-tuned control parameters and output responses considered by ITAE index, overshoot, rise time and steady state time.

A Greenhouse Control System Based on Best-Fitted PID Controller to Minimize Energy Cost

Vasanth Ragu,이명배,조용윤,박장우,신창선 한국지식정보기술학회 2018 한국지식정보기술학회 논문지 Vol.13 No.1

In these days, many of greenhouse environments are based on electric devices and ICT technologies. The model suggested in the paper the detailed design of a greenhouse control system adaptability with PID (Proportional Integral and Derivative) controller. Compared with a previous greenhouse control system (GCS), the proposed system is focused on the detailed design of greenhouse control process to minimize energy costs for crop growth in a greenhouse. In the suggested system, there are two important processes namely, Greenhouse Control Process (GCP) and Crop Growth Process (CGP). The two process data, which are crop status information and climate set-point information, are stored in an information storage database. The PID controller works inside the GCP and the environment control decision works inside the CGP. According to the service decision algorithm of it, the controller will work properly in a greenhouse. Using the suggested system with the different combinations such as P, PI, PD and PID, a user can easily simulate energy costs for a greenhouse system and efficiently design the best optimized controller in the greenhouse system. Therefore, the suggested system can provide a feasible solution to reduce or minimize energy cost in the greenhouse and help developments of various applications related with greenhouse environments.