论文部分内容阅读
为了及时准确掌握变压器的健康状况,对潜伏性故障进行预测分析,将人工智能算法与DGA算法相结合,提出了一种基于化学反应优化神经网络的变压器故障诊断模型。考虑到BP神经网络和传统DGA算法在变压器故障诊断应用过程中存在的缺陷,在模型中引入化学反应优化算法和融合DGA算法对其进行改进。通过实例分析表明,提出的故障诊断模型的诊断准确率达到87.88%,迭代次数和训练时间分别为1991次和1927 ms;与其他诊断模型相比,模型在诊断效率和训练时间上具有明显的优势,对于变压器的故障预测和实时诊断具有一定的参考意义。
In order to timely and accurately understand the health status of transformers, the latent faults were predicted and analyzed. Based on artificial intelligence algorithm and DGA algorithm, a fault diagnosis model of transformer based on chemical reaction optimization neural network was proposed. Considering the defects of application of BP neural network and traditional DGA algorithm in fault diagnosis of transformers, the chemical reaction optimization algorithm and the fusion DGA algorithm are introduced to improve the model. The case study shows that the diagnostic accuracy of the proposed fault diagnosis model reaches 87.88%, the number of iterations and training time are 1991 times and 1927 ms respectively. Compared with other diagnostic models, the model has obvious advantages in diagnosis efficiency and training time , It has a certain reference value for transformer fault prediction and real-time diagnosis.