This　study　try　to　address　the　challenge　of　anomaly　detection　in　Resistor-Capacitor　(RC)　circuits,　which　are　integral　to　modern　electronic　devices　and　susceptible　to　performance　deviations　due　to　a　range　of　factors.　Traditional　anomaly　detection　methods　often　fail　to　adapt　to　the　intricate　behaviors　of　advanced　circuit　designs.　In　response,　we　explore　the　efficacy　of　autoencoders,　a　deep　learning　architecture,　for　detecting　anomalies　by　learning　the　normal　operational　data　of　RC　circuits.　Specifically,　we　employ　PySpice,　a　Python　framework　integrated　with　Simulation　Program　with　Integrated　Circuit　Emphasis　(SPICE)　tools,　to　construct　a　simple　RC　circuit　and　generate　simulated　data.　Based　on　the　simulated　data,　autoencoders　function　by　encoding　input　data　into　a　compressed　latent　space　and　then　decoding　it　to　reconstruct　the　input.　Anomalies　are　identified　based　on　the　discrepancies　between　the　original　and　reconstructed　data.　Through　experimentation　on　simulated　RC　circuit　datasets,　we　validate　the　efficacy　of　the　autoencoder　model　in　anomaly　detection.　　©　2024　IEEE.