This paper proposes EventCluster, a novel approach in real-time data modeling. It deploys the Rank Order Clustering (ROC) method to automatically group all existing data sensors and actuators of the system to the Key Performance Indicators of the system. EventCluster (EC) is a cause-effect relationship data clustering tool that detects the interrelationship between field data and system performance parameters in real-time. Through its simple data filtering mechanism it can be used as a precursor to real-time sensitivity analysis. The underpinning logic of the technique is that the raw data can be obtained from field data acquisition devices and the degree of their influence on key system performance indicators can be measured in realtime with minimum computational effort. Normally monitoring and control systems are equipped with sensors and actuators that provide information for a pre-specified function regardless of other parts of the system. The global assumption of method is that a system performance or state is a function of all the inputs of the system, unless proven otherwise. In the proposed method all the inputs and outputs of the system are assumed to affect one another unless proven otherwise. In this paper, an experiment in Cement Kiln operation case demonstrates the suitability and applicability of EventClustering modeling method in industrial applications. We use the Supervisory Control and Data Acquisition (SCADA) sensors and actuators installed to monitor the operations of Kilns in Cement manufacturing process and its contagious operations as a case study for proof of concept. The sensors and actuators data collected builds the input data for measuring the performance (output) of the Kiln. The EventCluster algorithm resides within the control center of the SCADA system to assess the contribution of each input to the overall key performance indicators (output) of the process. This method improves the quality of data analysis and reduces computation ov- rhead on the control system.
展开▼
