• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1343-1346
• /
• 2005

In the cold rolling mill, coil breakage that generated in rolling process makes the various types of troubles such as the degradation of productivity and the damage of equipment. Recent researches were done by the mechanical analysis such as the analysis of roll chattering or strip inclining and the prevention of breakage that detects the crack of coil. But they could cover some kind of breakages. The prediction of Coil breakage was very complicated and occurred rarely. We propose to build effective prediction modes for coil breakage in rolling process, based on data mining model. We proposed three prediction models for coil breakage: (1) decision tree based model, (2) regression based model and (3) neural network based model. To reduce model parameters, we selected important variables related to the occurrence of coil breakage from the attributes of coil setup by using the methods such as decision tree, variable selection and the choice of domain experts. We developed these prediction models and chose the best model among them using SEMMA process that proposed in SAS E-miner environment. We estimated model accuracy by scoring the prediction model with the posterior probability. We also have developed a software tool to analyze the data and generate the proposed prediction models either automatically and in a user-driven manner. It also has an effective visualization feature that is based on PCA (Principle Component Analysis).

• IE interfaces
• /
• v.9 no.3
• /
• pp.298-305
• /
• 1996

Cold rolling mill process in steel works uses stands of rolls to flatten a strip to a desired thickness. Most of rolling processes use mathematical models to predict rolling force which is very important to decide the resultant thickness of a coil. In general, these mathematical models are not flexible for variant coil types and cannot handle various elements which is practically important to decide accurate rolling force. A corrective neural network is proposed to improve the accuracy of rolling force prediction. Additional variables-composition of the coil, coiling temperature and working roll parameters-are fed to the network. The model uses an MLP with BP to predict a corrective coefficient. The test results using 1,586 process data collected at POSCO in early 1995 show that the proposed model reduced the prediction error by 30% on average.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.5
• /
• pp.497-502
• /
• 1997

In this study an automatic rolling-coil labeling system using robot vision system and peripheral mechanism is proposed and implemented, which instead of the manual labor to attach labels Rolling-coils in a steel mill. The binary image process for the image processing is performed with the threshold, and the contour line is converted to the binary gradient which detects the discontinuous variation of brightness of rolling-coils. The moments invariant algorithm proposed by Hu is used to make it easy to recognize even when the position of the center are different from the trained data. The position error compensation algorithm of six degrees of freedom industrial robot manipulator is also developed and the data of the position of the center rolling-coils, which is obtained by floor mount camera, are transferred by asynchronous communication method. Therefore, even if the position of center is changed, robot moves to the position of center and performs the labeling work successfully. Therefore, this system can be improved the safety and efficiency.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.403-407
• /
• 2005

This paper proposes a looperless tension control algorithm which is robust to disturbance and tensional variation in rolling process using SVR(Support Vector Regression). Hot rolling process which is global technology to coil steel after continuous finishing process for welded bars followed by roughing mill process, becomes hot issue. Finishing mill process not only makes it possible to produce ultra thin steel strip(0.8 mm) but enhance the quality of terminals of coil, which increases the productivity due to faster process. Constant tension control between stands in hot rolling process is essential to enhance the quality of steel. Sensorless tension control is under research by some advanced companies to replace the conventional tension control method because in continuous finishing mill process, it is impossible to install the looper used in conventional control system. Simulation results show the effectiveness of the proposed algorithm.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.19 no.12
• /
• pp.1252-1259
• /
• 2009

Due to the international competition and global pressure, the roll speed is increased. However, higher speeds increase the power density in the process as well as the plant's potential to react with vibrations. Under certain operating conditions, vibrations may occur, which again cause chattermarks, strip rupture or coil break fault. The appropriate condition monitoring is needed to improve product quality and availability. The aim of condition monitoring is to reduce maintenance costs, increase productivity and improve product quality. This paper proposes a condition monitoring tool designed for the classification of coil break fault. This method is used to cold rolling mill for faults monitoring based on vibration and motor current signals. The results show that the performance of classification has high accuracy based on experimental work.

• Proceedings of the KIEE Conference
• /
• 2005.04a
• /
• pp.73-75
• /
• 2005

이 논문에서는 전기강판의 자계 특성을 측정하기 위하여 이방향 자계인가형 싱글 시트 테스터가 개발되어졌다. 이 개발된 시스템은 자속밀도와 자계세기를 B-coil과 H-coil로 측정할 수 있다. B-coil은 rolling direction과 transverse direction에 대하여 각각 1-turn 감겨져 있으며 H-coil은 200-turn 각각 감겨져있다. 실험을 통하여 이 시스템은 방향성 전기 강판의 경우 rolling direction에 대하여 1.8 [T]까지 측정되어질 수 있다.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.54 no.10
• /
• pp.461-469
• /
• 2005

In this paper, a double-excitation type single sheet tester is developed to measure the magnetic characteristics of the electrical steel sheets. The developed system has the uniform magnetic field area of 20$\times$20mm$^{2}$, and can be applied to the measurement of the magnetic characteristics of the Non-oriented and Grain oriented electrical steel sheets. In the developed system, the magnetic flux density and magnetic field intensity are measured by using B-coil and H-coil, respectively. The B-coil has 1 turn search coil for each direction, and H-coil has 640 and 640 turns for rolling direction and transverse direction on the Im thickness Glass-Epoxy basement, respectively. Through experiments, it Is shown that the system can measure the magnetic characteristics up to 1.87 of magnetic flux density in the rolling direction in case of the Grain oriented electrical steel sheet. The measured results are compared with those measured in Okayama university, .Japan.

• IE interfaces
• /
• v.16 no.2
• /
• pp.248-257
• /
• 2003

In a heated rolling process of a steel mill where steel plates are pressed to a sheet coil by spreading and expanding, an irregularly-shaped head portion as well as a tail portion of the sheet coil need to be cropped. Any crop which is not clearly cut and separated from the sheet coil may cause critical damages to the facilities of the following processes. As the cropping process is performed very fast, human eyes are not proper for continuous monitoring of the cropping process. To solve this problem, we have developed a machine-vision based crop-drop detection system. The system also measures lengths of major and minor axes for the crops and thereby determines the proper crop size to minimize steel sheet losses.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.10
• /
• pp.1007-1011
• /
• 2007

This paper proposes a novel tension estimation of interstand strip in looperless hot rolling process using SVR(Support Vector Regression). The quality of hot coil which is final product of hot rolling process is substantially decided by tension control of finishing rolling in hot rolling process. The fluctuation of the strip tension in conventional hot rolling process is controlled by the strip tension measured by an inter-stand looper. However, the looper can cause a motor trip and tension hunting in hot rolling process, therefore, alternative method is essential to replace it. In this paper, the mathematical modeling of tension mechanism is implemented to estimate the tension using the proposed SVR algorithm without looper in hot rolling process. The simulation results show a reliable estimation performance and a possibility of tension control using SVR technique.

• Transactions of Materials Processing
• /
• v.3 no.1
• /
• pp.63-83
• /
• 1994

In this paper, the slab method have been applied to investigate the strip casting process in which hot coil is produced from molten steel directly. In the twin roll strip casting process, molten steel supplied by the nozzle cools and solidifies due to the heat extraction effect of the rolls and hot rolling of the solidified shell takes place simultaneously. The analysis of hot rolling has been carried out by using the existing results of solidification analysis for the twin roll strip casting process. The current slab method provides basic design data such as roll separation force, rolling torque, rolling power as well as end dam separation force which are required to design strip caster. The effect of friction on the basic process parameters are investigated also. It is shown that the use of appropriate friction coefficient is important and that the characteristics of hot rolling in the twin-roll strip casting process is quite different from the conventional hot rolling processes.