• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.6
• /
• pp.749-756
• /
• 2021

Thanks to PLC and IoT Sensor, huge amounts of data has been accumulated onto the companies' databases. Machine Learning Algorithms for the predictive model with good performance have been widely utilized in the manufacturing process. We present how to improve the performance of machine learning predictive models. To improve the performance of the predictive model, typical techniques such as increasing the sample size, optimizing the hyper parameters for the algorithm, and selecting a proper machine learning algorithm for the predictive model would be shown. We suggest some new ways to make the model performance much better. With the proposed methods, we can build a better predictive model for predicting and controlling product qualities and save incredibly large amount of quality failure cost.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.9-16
• /
• 2018

Predictive control is a very practical method that obtain the current input that minimizes the future errors of the reference command and state by use of the predictive model of the controlled object, and can also consider the constraints of the state and input. Although there have been studies in which predictive control is applied to mobile robots, performance has not been optimized as various control parameters for determining control performance have been arbitrarily specified. In this paper, we apply the genetic algorithm to the trajectory tracking control of a mobile robot with input constraints in order to minimize the trajectory tracking errors through control parameter tuning, and apply the quadratic programming Hildreth method to reflect the input constraints. Through the computer simulation, the superiority of the proposed method is confirmed by comparing with the existing method.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.145-149
• /
• 1993

This paper considers the adaptive predictive control problem of a system characterized by a multiplexed measurements and multirate sampling mechanism. Plant outputs are measured in various sampling rates through a multiplexed measurement system where a single common instrument is shared by several controllers. In general, output measurement sampling rate is assumed to be slower that input update rate. An adaptive predictive control algorithm is developed for systems with multiplexed measurements.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.490-495
• /
• 1992

A neural model predictive control strategy combining a neural network for plant identification and a nonlinear programming algorithm for solving nonlinear control problems is proposed. A constrained nonlinear optimization approach using successive quadratic programming cooperates with neural identification network is used to generate the optimum control law for the complicate continuous/batch chemical reactor systems that have inherent nonlinear dynamics. Based on our approach, we developed a neural model predictive controller(NMPC) which shows excellent performances on nonlinear, model-plant mismatch cases of chemical reactor systems.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.143-143
• /
• 2000

A neural net based generalized predictive control(NNGPC) is presented for a hydraulic servo position control system. The proposed scheme employs generalized predictive control, where the future output being generated from the output of artificial neural networks. The proposed NNGPC does not require an accurate mathematical model for the nonlinear hydraulic system and takes less calculation time than GPC algorithm if the teaming of neural network is done. Simulation studies have been conducted on the position control of a hydraulic motor to validate and illustrate the proposed method.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.899-902
• /
• 1993

A neural model predictive control strategy combining a neural network for plant identification and a nonlinear programming algorithm for solving nonlinear control problems is proposed. A constrained nonlinear optimization approach using successive quadratic programming combined with neural identification network is used to generate the optimum control law for complex continuous chemical reactor systems that have inherent nonlinear dynamics. The neural model predictive controller (MNPC) shows good performances and robustness. To whom all correspondence should be addressed.

• Proceedings of the KIEE Conference
• /
• 1995.07a
• /
• pp.340-343
• /
• 1995

This paper consists of the position control of induction motor using Generalized Predictive Control. Full order flux observer is also used for the purpose of estimating rotor fluxes. By using Generalized Predictive Control algorithm, the improved position control is realized in this paper. The proposed control method has been implemented by a 32 bit floating point TMS320C31 DSP chip.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.299-302
• /
• 1996

A control algorithm is proposed for nonlinear multi-input multi-output(MIMO) batch processes by combining quadratic iterative learning control(Q-ILC) with model predictive control(MPC). Both controls are designed based on output feedback and Kalman filter is incorporated for state estimation. Novelty of the proposed algorithm lies in the facts that, unlike feedback-only control, unknown sustained disturbances which are repeated over batches can be completely rejected and asymptotically perfect tracking is possible for zero random disturbance case even with uncertain process model.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.977-980
• /
• 2007

Observer design for the nonlinear systems is known to be difficult in general. This paper suggests a feedback GA-based model predictive observer for the observable systems. Feedback concept makes on-line design possible for the cases including observer design, where GA is implemented repeatedly every time instant. The effectiveness of our observer is shown by simulation.

• Journal of Periodontal and Implant Science
• /
• v.48 no.2
• /
• pp.114-123
• /
• 2018

Purpose: The aim of the current study was to develop a computer-assisted detection system based on a deep convolutional neural network (CNN) algorithm and to evaluate the potential usefulness and accuracy of this system for the diagnosis and prediction of periodontally compromised teeth (PCT). Methods: Combining pretrained deep CNN architecture and a self-trained network, periapical radiographic images were used to determine the optimal CNN algorithm and weights. The diagnostic and predictive accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve, area under the ROC curve, confusion matrix, and 95% confidence intervals (CIs) were calculated using our deep CNN algorithm, based on a Keras framework in Python. Results: The periapical radiographic dataset was split into training (n=1,044), validation (n=348), and test (n=348) datasets. With the deep learning algorithm, the diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars. Using 64 premolars and 64 molars that were clinically diagnosed as severe PCT, the accuracy of predicting extraction was 82.8% (95% CI, 70.1%-91.2%) for premolars and 73.4% (95% CI, 59.9%-84.0%) for molars. Conclusions: We demonstrated that the deep CNN algorithm was useful for assessing the diagnosis and predictability of PCT. Therefore, with further optimization of the PCT dataset and improvements in the algorithm, a computer-aided detection system can be expected to become an effective and efficient method of diagnosing and predicting PCT.