A prediction method for mold breakout based on feature vectors and hierarchical clustering is disclosed, which comprises: respectively extracting temperature feature vectors of historical data under sticking breakout and normal conditions and on-line actually measured data to establish a feature vector sample set; performing normalization and hierarchical clustering on the sample set; and checking and judging whether the feature vectors extracted on line belong to a breakout cluster, and then identifying and predicting mold breakout. The method avoids the steps of tedious adjustment and modification of alarm threshold and other parameters, overcomes the artificial dependence of the previous breakout prediction method, has good robustness and mobility; and through temperature feature extraction, achieves accurate identification of sticking breakout temperature patterns, avoids missing alarms and significantly reduces the number of times of false alarms, and greatly reduces the data calculation amount and calculation time, guaranteeing the timeliness of on-line prediction.

A prediction method for mold breakout based on feature vectors and hierarchical clustering is disclosed, which comprises: respectively extracting temperature feature vectors of historical data under sticking breakout and normal conditions and on-line actually measured data to establish a feature vector sample set; performing normalization and hierarchical clustering on the sample set; and checking and judging whether the feature vectors extracted on line belong to a breakout cluster, and then identifying and predicting mold breakout. The method avoids the steps of tedious adjustment and modification of alarm threshold and other parameters, overcomes the artificial dependence of the previous breakout prediction method, has good robustness and mobility; and through temperature feature extraction, achieves accurate identification of sticking breakout temperature patterns, avoids missing alarms and significantly reduces the number of times of false alarms, and greatly reduces the data calculation amount and calculation time, guaranteeing the timeliness of on-line prediction.

A system for detection of the level of a liquid metal within a crystallizer of a mold has a detection system. The detection system is based on a transmission of at least one signal transmitted toward a crystallizer having the liquid metal therein and a reception of a reflection of the transmitted signal. A first ultrasonic element transmits a ultrasonic elastic wave and a second ultrasonic element receives the ultrasonic elastic wave. A processor measures a time elapsed between transmission and reception and correlates the elapsed time relative to the level of liquid metal in the crystallizer.

Provided herein are an apparatus and method for continuous casting of metal, and more particularly, to an apparatus and method to reduce macrosegregation through a mechanism for controlling the position of a spout tip or diffuser during the casting process to maintain the spout tip or diffuser near the solidification front, location of transition between liquid metal and solid metal in the cast part. An apparatus may include: a mold frame supporting a mold defining a mold cavity; a liquid diffuser; and an actuator configured to move at least one of the mold frame and the liquid diffuser relative to one another, wherein the actuator is configured to move at least one of the mold frame and the liquid diffuser relative to one another in response to a signal from at least one sensor.

A control method of a continuous casting process is a method that injects molten metal from a surface layer nozzle and an inner layer nozzle into a mold and separates the molten metal of a surface layer and the molten metal of an inner layer, the control method including, using a molten metal level meter that measures a surface layer level and a flowmeter that measures a supply flow rate of the molten metal, estimating a boundary layer level on the basis of a measured value of the surface layer level, a measured value of the supply flow rate of the molten metal, and a calculated value of the supply flow rate of the molten metal, and controlling the supply flow rate of the molten metal of the surface layer nozzle and the supply flow rate of the molten metal of the inner layer nozzle.

A control method of a continuous casting process is a method that injects molten metal from a surface layer nozzle and an inner layer nozzle into a mold and separates the molten metal of a surface layer and the molten metal of an inner layer, the control method including, using a molten metal level meter that measures a surface layer level and a flowmeter that measures a supply flow rate of the molten metal, estimating a boundary layer level on the basis of a measured value of the surface layer level, a measured value of the supply flow rate of the molten metal, and a calculated value of the supply flow rate of the molten metal, and controlling the supply flow rate of the molten metal of the surface layer nozzle and the supply flow rate of the molten metal of the inner layer nozzle.

Steam exhaust ports are located around a perimeter of a direct chill casting pit, at various locations from below the top of the pit to the pit bottom to rapidly remove steam from the casting pit with addition of dry excess air. Gas introduction ports are also located around a perimeter of the casting pit and configured to introduce an inert gas into the casting pit interior.

Steam exhaust ports are located around a perimeter of a direct chill casting pit, at various locations from below the top of the pit to the pit bottom to rapidly remove steam from the casting pit with addition of dry excess air. Gas introduction ports are also located around a perimeter of the casting pit and configured to introduce an inert gas into the casting pit interior.

A prediction method for mold breakout based on feature vectors and hierarchical clustering is disclosed, which comprises: respectively extracting temperature feature vectors of historical data under sticking breakout and normal conditions and on-line actually measured data to establish a feature vector sample set; performing normalization and hierarchical clustering on the sample set; and checking and judging whether the feature vectors extracted on line belong to a breakout cluster, and then identifying and predicting mold breakout. The method avoids the steps of tedious adjustment and modification of alarm threshold and other parameters, overcomes the artificial dependence of the previous breakout prediction method, has good robustness and mobility; and through temperature feature extraction, achieves accurate identification of sticking breakout temperature patterns, avoids missing alarms and significantly reduces the number of times of false alarms, and greatly reduces the data calculation amount and calculation time, guaranteeing the timeliness of on-line prediction.

A method of controlling an electromagnetic stirrer arranged around a submerged entry nozzle (SEN) of a tundish provided with a stopper rod to control throughput of the tundish, the SEN being configured to provide tapping of molten metal from the tundish and the electromagnetic stirrer being configured to generate a rotating magnetic field in the SEN, wherein the method includes controlling the electromagnetic stirrer to operate only when a gas flow rate through the stopper rod is in a first range of 1.5 NL/min to 20 NL/min.