Self-managing systems are a significant feature in autonomic computing; required for a system's reliability and performance in a changing environment. The work described in this paper is concerned with self-healing systems; systems that can detect and analyse issues with their behaviour and performance, and enact fixes or reconfigurations as appropriate. These processes should occur in a real-time manner, restoring desired functionality as soon as possible. The system should ideally maintain functionality during the healing process, occurring at runtime. Neural networks, specifically recursive networks, are proposed as a solution to some of these challenges; monitoring the system and environment, mapping a suitable resolution and adapting the system accordingly. A novel application of a modified pipelined recurrent neural network is proposed in this paper with experiments aimed to assess the applicability to online, at runtime, adaptation with multiple input variables. The first set of experiments applies a pipelined recurrent neural network to control server requests across a bank of servers, routing and adding/removing capacity to maximise efficiency and ensure service quality. The second experiments supplement an overcurrent relay with a pipelined recurrent neural network, monitoring, and if necessary, replicating its circuit breaking functionality as required based on line signal measurements.