The article aims to develop a physics-informed neural network (PINN) for parameter identification in a piezoelectric harvester using experimental sampling data. The advantage of PINN lies in its efficient inverse calculation of parameters with minimal sampled signals. For instance, with a single piezoelectric oscillator, the data collection process requires only two sets of piezoelectric voltage waveforms acquired at different electric loads and excitation frequencies. The training process involves minimizing the loss function, which comprises the model-based differential equations and the sampled time-domain voltage signals. The results successfully achieve inverse parameter identification, covering mechanical damping ratio, capacitance, and voltage source (force magnitude divided by the piezoelectric constant). In addition, the voltage frequency response, based on the inverse parameters, agrees well with experimental observations, confirming the model's reliability.