Smart building applications require robust security measures to ensure system functionality, privacy, and security. To this end, this paper proposes a Federated Learning Intrusion Detection System (FL-IDS) composed of two convolutional neural network (CNN) models to detect network and IoT device attacks simultaneously. Collaborative training across multiple cooperative smart buildings enables model development without direct data sharing, ensuring privacy by design. Furthermore, the design of the proposed method considers three key principles: sustainability, adaptability, and trustworthiness. The proposed data pre-processing and engineering system significantly reduces the amount of data to be processed by the CNN, helping to limit the processing load and associated energy consumption towards more sustainable Artificial Intelligence (AI) techniques. Furthermore, the data engineering process, which includes sampling, feature extraction, and transformation of data into images, is designed considering its adaptability to integrate new sensor data and to fit seamlessly into a zero-touch system, following the principles of Machine Learning Operations (MLOps). The designed CNNs allow for the investigation of AI reasoning, implementing eXplainable AI (XAI) techniques such as the correlation map analyzed in this paper. Using the ToN-IoT dataset, the results show that the proposed FL-IDS achieves performance comparable to that of its centralized counterpart. To address the specific vulnerabilities of FL, a secure and robust aggregation method is introduced, making the system resistant to poisoning attacks from up to $20\%$ of the participating clients.