The increasing integration of artificial intelligence in Industry 4.0 networks makes explainable models crucial for ensuring the transparency and trustworthiness of security protocols. This paper proposes a particular Explainable AI-Based Discrete Swarm Herd Optimization model for intrusion detection as a solution to the distinct security challenges with Industry 4.0 environments. The proposed system reduces the number of false positives around network anomalies and threats, using swarm intelligence for optimal feature selection and classification. The proposed model utilizes explainable AI techniques so that the operators can understand how the system works, thereby allowing better responses towards security threats. The DSHO algorithm is characterized as discrete, thus ensuring an efficient handling of high-dimensional data in industrial networks while being computationally efficient. Further, a fuzzy logic-based approach for prioritizing intrusion risks is integrated to further refine response actions. This method improves continuously by interacting with real-world network data and thus gives a dynamic and adaptive intrusion detection solution. The usage of explainable AI will provide transparency, and this would enable the administrators to understand the results appropriately for improved overall network security when compared to other existing works. The model will be up to date with periodic updations and allows effective prevention of constantly evolving cyber threats. It has been seen to contribute immensely towards Industry 4.0 network security from sophisticated attacks.