Abstract: To address the challenges of scarce domain-specific corpora for electromechanical equipment, insufficient feature mining for relation types, and the presence of overlapping triplets in texts, a triplet extraction method based on learning with prior knowledge through iterative adversarial training was proposed. Firstly, the BERT model was fine-tuned on a self-constructed corpus to obtain feature vectors for input texts. Then, an iterative adversarial training using the Projection Gradient Descent (PGD) method was conducted at the embedding layer to enhance the model's resistance to perturbed samples and generalization ability to real samples. Furthermore, a single-layer head-tail pointer network was used to identify the head entity, and domain-specific prior features corresponding to the head entity were obtained by incorporating the word vectors with the vectors predicted by the learning template. Finally, within a hierarchical annotation framework, another single-layer head-tail pointer network was employed to sequentially identify the tail entities associated with predefined relation types. In comparison with the baseline model CasRel, the proposed method achieves improvements of 3.10, 6.12, and 4.88 percentage points in precision, recall, and F1 score, respectively. Experimental results demonstrate its advantages in triplet extraction tasks within the domain of coal mining electromechanical equipment.