Application of continuous probabilistic networks to leak detection in pipe-type cable installations

This paper discusses application of continuous probabilistic networks to leak detection in high-pressure, fluid-filled (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.