Data mining of sensor monitoring time series and knowledge discovery

The sensor monitoring data coming from complex industry environment is the main real-time dependence for people working in the manufacture monitoring center to know the field operation condition. Using the data mining techniques to discover the regularity knowledge from the sensor monitoring database is very important for the supervisors to identify the reason causing the exceptional fluctuation automatically and make the correct decisions promptly. Exceptional time series clustering based on the DTW distance is proposed firstly, thus the typical time series patterns can be obtained. From which the important shape indexes can be extracted and filtered based on piecewise shape measure method. At last, the knowledge used to recognize the exceptional pattern can be abstracted from the shape feature table and represented with the first order predicate logic language. As an example, the important promotion application value of this set of method using in a high gas coal mine is proved in the sensor monitoring field.