Automatic surveillance of hot rolling area against intentional attacks and faults

ended

Is a hot rolling mill secured against intentional attacks? Could a re-heating furnace or the accelerated cooling be used for sabotaging the quality of a European steel producer? How can attacks be separated from fault behaviour? AutoSurveillance will provide a solution for detecting anomalies in re-heating furnaces, hot-rolling mills and accelerated cooling, a solution that is capable of announcing a threat and in parallel distinguishing between faults and intentional attacks. It focusses on the process-oriented treatment of such occurrences and explicitly not on the IT perspective. The project consortium of AutoSurveillance concluded that there is urgent need to increase the security of control system in European steel plants from an inner process perspective and not to trust in the security an outer IT environment can offer. Therefore any successful novel kind of detection, healing and resilient strategy must be founded on the process knowledge itself. Although the occurrence of such events is actually rather low, the economic stakes of such an event are unbearable high for the European steel industry: the consequences are production out-times, damaged machinery and repair activities, all of which eat up man-hours and money in an excessive way. It hardens the automation system against it on process level. Many other effects can obfuscate or obscure the view on the process, such as sensor and actuator uncertainties and process anomalies. To detect intentional sabotage, one must prior exclude things like drifts or errors in the measurements and unintentional process anomalies caused by the instability of process situations. Hence there is a need for monitoring control systems online, to detect any kind of abnormal behaviour. Sensorial deficiencies, actuator malfunctioning or process perturbations must be elemental part of a system that secures against intentional damages!