Autonomous and adaptive procedure for cumulative failure prediction

Abstract

An autonomous adaptive reliability prediction model using evolutionary connectionist approach based on Recurrent Radial Basis Function architecture is proposed. Based on the currently available failure time data, Fuzzy Min-Max algorithm is used to globally optimize the number of the k Gaussian nodes. This technique allows determining and initializing the k-centers of the neural network architecture in an iterative way. The user does not have to define arbitrary some parameters. The optimized neural network architecture is then iteratively and dynamically reconfigured as new failure occurs. The performance of the proposed approach has been tested using sixteen real-time software failure data.

Proposing a Layer to Integrate the Sub-classification of Monitoring Operations Based on AI and Big Data to Improve Efficiency of Information Technology Supervision

“…Earlier works have focused on improving the efficiency of the monitoring process by dealing with large amounts of data to be collected, analysed, and stored [24]- [26], and even if the problems of critical limits induced by monitoring process actions related to the processing power are overcome. Despite this fact, the overload of bandwidth and storage capacity remains a major challenge, as does identifying important events among vast amounts of measurement data, visualizing them, and interpreting them to make decisions and detect failures [27].…”