In Wireless Sensor Networks (WSN), intrusion detection during sensor monitoring enables the identification of intricate, occasionally minute security threats such as denial-of-service and routing attacks. Moreover, monitor security is compromised by their susceptibility to intrusions and the possibility of data manipulation. To build a monitoring system that is trustworthy, energy-efficient, and impervious to risks to internal security. To overcome this problem, intrusion detection systems (IDSs) are used to remotely monitor the behavior and performance of nodes that are a part of wireless sensor networks. Generally speaking, IDSs are not just able to identify rogue nodes within a network; they can also predict their behavior in the future. Therefore, to introduce a System IDS (NIDS) termed (FSS, FLN in MOPSO), the suggested study integrated a Fast Learning Network with Feature Subsection Selection (FSS) based on Multi Objective Particle Swarm Optimization (MOPSO). The simulation results show that this approach, in contrast to previous approaches, can balance the goals of the number of representative features and training errors based on MOPSO’s evolutionary capability, thereby improving the performance of the IDS in terms of evaluation criteria. Along with an increase in average remaining energy, packet delivery ratio, and packet loss ratio, the numerical analysis also shows that the network’s life cycle is extended. Along with an increase in average remaining energy, packet delivery ratio, and packet loss ratio, the numerical analysis also shows that the network’s life cycle is extended.