A system to monitor a regulator placed in a ventilation network by combination of human recognition and computer simulation

To maintain good condition of ventilation for both safety and economy, many regulators are installed in a network. In case the open state of a regulator is different from the set point, identification of a broken regulator and a countermeasure to recover airflow distribution in a network must be initiated as soon as possible. An experienced mining engineer can sense a deviation from ordinary airflow quantity. In this paper, a new system to monitor all the regulators in a network is introduced. The basic concept of the system is utilization of both human sensing of airflow rate and computer simulation to understand the macroscopic characteristics of a ventilation network. A fuzzy pattern distinction method is used to process human determination of airflow rate that may be ambiguous. The applicability of the system is demonstrated using the ventilation network of the Horonai coal mine, Japan. In particular, it is shown that the system can identify the regulator to be repaired from information supplied by workers relating to airflow in a few sensor branches.