A heat engine often coined as a system transmutes thermic and chemic energies to mechanical energy. The current review employs a traditional heat engine, i.e., an internal combustion engine, where a self-automated optimization technique is incorporated for determining best optimal parameters and for diagnosing the flaws thereby enhancing the overall efficacy. Several difficulties are witnessed during the effective functioning of an IC engine which eventually roots to multiple energy losses leading to the fatigue failure of the entire system. The current review engages a self-acting conceptualization for characterizing the several faults which deteriorates the overall performance traits. In contrast to the prevailing methodologies, viz. radiated sound signal, wavelet carton disintegration, the novel existent artificial neural network (ANN) methodology engages an extension pattern recognition technique encompassing an input skin and output skin. This simple, novel extension neural network (ENN) renders amplified optimization results and much easier data incorporation in contrast to the conventional neural networks. The current study is successful in devising a novel, self-automated, efficient diagnostic system. The inferences drawn from this novel technique tend to have superior optimization and fault identification rates.