This paper focuses on the tracking control problem for switched nonlinear ship maneuvering time-delay systems with only a heading angle available by adaptive neural network (NN) output feedback. Using the backstepping method, an adaptive NN control mechanism is designed to solve the problem cooperated with the state observer. The uncertain terms of the system are approximated by NNs, and the state observer is designed to estimate the yaw rate and rudder angle. The unknown time delays are overcome by exploiting the common Lyapunov-Krasovskii functionals (CLKFs). Combined with error transformation, the proposed control method guarantees that i) all of the signals for the system are semi-global uniformly ultimately boundedness (SGUUB) under arbitrary switching; and, ii) the tracking error of system output keeps within a small neighborhood around the origin. The results of simulation results are shown to demonstrate the feasibility of the control strategy.