Fault detection framework based on data-driven system identification, applicable for large-scale sensor networks. Hybrid memetic learning method for Takagi–Sugeno fuzzy systems (combining sparse with heuristics-based optimization). Parameter and structural solutions closer to optimality inducing higher predictive quality of fuzzy models. Adaptive filter design for incrementally smoothening residual signals in a data-streaming context (single-pass). Significant improvement of fault detection rates over state-of-the-art while ensuring very low false positive rates.