Analog circuit test point selection method for fault diagnosis based on deep reinforcement learning

Reliable operation of analog circuits is fundamental to the safety of medical instruments, automotive controllers, and aerospace systems. A prerequisite for effective fault diagnosis is the selection of a compact yet informative set of test nodes, commonly referred to as analog test-point selection (ATPS). Existing optimization- and search-based approaches often exhibit slow convergence and susceptibility to sub-optimal solutions when applied to large-scale circuits. In this study, ATPS is reformulated as a sequential decision-making problem addressed by a Dual-Stream Dueling Deep-Q Network (DS-DDQN). The framework is designed to learn, from simulation data, the most valuable next test node under a user-defined cost constraint. Two types of input are processed: the evolving diagnostic state, representing unresolved fault groups, and the available cost budget. To achieve scalability, raw simulation responses are compressed into compact fault-isolation scores through a Gaussian mixture model, allowing efficient learning even in the presence of extensive fault dictionaries. Experimental evaluations on industry-standard benchmarks and real-world circuits demonstrate improvements in diagnostic accuracy from 3.94% to 33.72% and reductions in selection time by nearly an order of magnitude, compared with circuit-level outputs and representative baseline methods.