Detection of fluid leaks in pipe-type cable installations is important for both environmental and operational reasons. A new application of modern numerical algorithms, such as neural and probabilistic networks, for monitoring pressure system installations has been recently presented by the authors. This approach led to the development of a complete system for monitoring highpressure, fluid-filled cables. During the initial system implementation, a need arose for the detection of very small leaks. To meet this need, the detection algorithms were revised and new features were implemented. This paper describes the new algorithms and discusses their implementation.Index Terms-Dielectric fluid leak detection, neural networks, pipe-type cables, probabilistic networks.
This paper discusses application of continuous probabilistic networks to leak detection in high-pressure, fluidfilled (HPFF) cables. An existing system for leak detection, build on discrete network, has a number of drawbacks -mainly the probability specification is difficult and quantization of input data has to be performed. An approach using continuous functions is proposed in the paper, which overcomes some restrictions of continuous probabilistic networks found in the literature. It introduces an algorithm for efficient utilization of the nonlinear functions in continuous networks. The existing discrete network, for assessing leak probability, is replaced with a continuous one. Number of tests is performed to verify operation of the leak detection system with the new network type.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.