Abstract
Theoretical analysis revealed that in order to create learning fire detectors, capable of adjusting to unknown conditions of application, it is expedient to consider the criterion of equality of probabilities of false detection and skipping a fire as a criterion of guaranteed fire detection. By using such detection criterion, it is possible to provide guaranteed fire detection under conditions of the absence of a priori information about statistics of the recorded data. The algorithms and structural circuits of the learning fire detectors were developed for the case of discrete and continuous data recording by sensors. Their distinguishing feature is the possibility of application under indeterminate conditions when there is no a priori information about the type of distribution laws of the recorded data, as well as their capability to adapt to previously unknown and changing application conditions and to provide guaranteed fire detection in this case. It was shown that the main limitation in the implementation of such algorithms is the need to use additional instructions from a trainer about the existence or the absence of a fire on the object. To overcome this limitation, it is proposed to apply the hypothesis about sufficient rarity of events related to a fire on the protected sites. This made it possible to use the registered information about the absence of fire as the instructions from a trainer. In this case, the resulting modified algorithm and the structural circuit of the proposed fire detector that matches it do not require instructions from a trainer and, in this sense, a detector becomes a self-learning fire detector. Results of examining the fire detectors, performed based on the example of real dynamics of the mean temperature of medium when alcohol is ignited and burned, demonstrated their high efficiency. In comparison with fire detectors that comply with the requirements of standard EN 54-5:2003, the examined self-learning fire detectors possess an essential gain in time (exceeding 170 times) of the guaranteed fire detection on the site under uncertain conditions. The ability of self-learning fire detectors to adapt to previously unknown conditions allows their application under non-stationary conditions in order to detect complex fires.
Highlights
Considerable attention has been recently paid to the problem of creation of learning systems, which are capable of improving their functioning in the course of time
The studies described in the scientific literature are based on the assigned statistics of data, observed or recorded by fire detectors (FD), and do not tackle the problem of the guaranteed detection and creation of FD capable of learning under uncertain conditions. This means that the problem of guaranteed fire detection by FD on actual sites is solved predominantly with complete a priori information based on known statistical technologies
Structural circuits that realize the given algorithms and which are outlined in Fig. 1, 2 will represent nonlinear systems, which correspond to the learning and self-learning FD for the guaranteed fire detection under conditions of uncertainty
Summary
Considerable attention has been recently paid to the problem of creation of learning systems, which are capable of improving their functioning in the course of time. The actual conditions of applying fire automation systems are so diverse and unpredictable that it does not seem possible to create a system, which would provide the guaranteed fire-prevention protection of different sites within the framework of systems with fixed parameters. High demands are imposed on thermal FD, used in the systems of early fire detection when the initial dynamics of an increase in the ambient temperature is disguised by unpredictable random temperature disturbances In this connection, in order to provide a reliable fire-prevention protection of objects, the problem of creation of learning FD acquires special relevance. In order to provide a reliable fire-prevention protection of objects, the problem of creation of learning FD acquires special relevance They are capable of improving their functioning and provide guaranteed fire detection on the sites under actual application conditions. The relevance of the work in this direction is in the development of learning FD and in examining their dynamic properties under conditions of real dynamics of the mean temperature of medium taking into account the unpredictability of temperature disturbances when a fire starts
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Eastern-European Journal of Enterprise Technologies
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
