To reduce the nuisance alarm rate (NAR) in phase-sensitive OTDR sensing system, a novel event identification model based on principal component analysis (PCA) and probabilistic neural network (PNN) is proposed. By training a PCA-PNN model, five kinds of disturbance events including four kinds of real disturbance and one kind of false disturbance can be effectively identified. Experimental results indicate that the average identification rate of five kinds of events reach 97.74%, with an average response time of 0.93 s. Multiple events identification with a high identification rate and fast response makes the proposed method more adaptable in practical application.

为了降低相敏OTDR传感系统中的有害警报率（NAR），提出了一种基于主成分分析（PCA）和概率神经网络（PNN）的新型事件识别模型。通过训练PCA-PNN模型，可以有效地识别出五种干扰事件，包括四种真实干扰和一种虚假干扰。实验结果表明，五种事件的平均识别率达到97.74％，平均响应时间为0.93 s。具有高识别率和快速响应的多事件识别使得该方法在实际应用中更加适应。