The BPS-K600 continuous casting mould breakout prediction system is developed by Wuhan CenterRise M&C Measuring Co., Ltd. It adopts artificial neural network and combines with traditional artificial intelligence and information processing technology to overcome the defects of traditional logic-based prediction models. It has the functions of self-adaptation, self-organization and real-time learning.

The breakout prediction system has an optimized industrial network structure. According to the distribution and change rules of the temperature field of the mold, it can track and respond to the breakout process in real time. It can learn and judge by itself, and provide early warning information for on-site operations. It can effectively prevent the occurrence of breakout accidents, greatly reducing the cost and improving the safety factor of continuous casting.

The system is suitable for all kinds of continuous casting machines such as square billet, round billet, rectangular billet and slab.



Block Diagram of Breakout Prediction System



The composition of the system

Thermocouple: according to the on-site conditions of the mold, water tank, bolts and mold frame to desgin

Front-end acquisition system: Multi-module acquisition chain, industrial Ethernet interface, high-speed embedded processing module

Working platform: Real-time display of mold temperature field status, online analysis and prediction of mold breakout

Server: Data exchange and storage management, reporting and printing system, with data analysis and self-learning functions



The Main technical parameters

Data sampling: the sampling frequency of K-type/T-type thermocouple can up to 10HZ

Accuracy of temperature measurement: ±0.25℃

Support communication protocol: Industrial Ethernet (TCP/IP)，PROFIBUS-DP，CANopen

Executive standard: DE0411 Standard Class III/1EC584/IEC1515

Transmission speed: 100M/bps



The composition of the software

Online monitoring software for breakout prediction

Offline query software for breakout prediction

Data recovery and self-learning software packages

Data acquisition and monitoring software

The software package of mold thermal status display







The functions of the system

Real-time data acquisition, data analysis and judgment

Automatic selection of steel grade’s alarm parameters

Real-time dynamic picture monitoring

Prediction alarm and information display of breakout signs

Automatic deceleration after alarm

Historical data storage and historical trend graph display

Automatic report generation and printing

Alarm prediction and pattern recognition of unknown steel grades by neural network

Dynamic real-time temperature profile prediction

Mould heat flow field display







FIG 1：Typical process of mold breakout prediction

The features of the system

1. Reasonable design of temperature measurement point and profes

Contact