基于人工智能的大电机主绝缘老化状态评估软件

为了更有效地评估大电机主绝缘的老化状态,提出了应用神经网络和模糊数学相结合的人工智能技术评估绝缘老化状态的新方法。首先,建立具有模糊输出的3层反向传播(BP)神经网络,并确定绝缘状态论域上的4个模糊子集及其隶属函数,同时规定了模糊输出神经网络的输入和输出参量;然后,选择Levenberg-Marquardt快速学习算法对建立的模糊输出神经网络进行训练,并使用真机线棒数据对网络的评估效果进行检验;最后,基于MATLAB开发了大电机主绝缘老化状态智能评估软件。研究结果表明该软件可以准确有效地评估定子绝缘的老化状态。

Evaluating Software for Aging Condition of Main Insulation Based on Artificial Intelligence Technology

The condition assessment of large generator main insulation is an important research subject in electrical engineering field, and the key destination is to assess the aging condition of insulation based on the nondestructive parameters. A new artificial intelligent assessment method based on the combination of fuzzy math theory and artificial neutral network (ANN) is proposed in order to overcome the disadvantages of traditional insulation condition assessment based on the threshold model. Firstly, the 3 layers of BP ANN are established with 4 fuzzy outputs, which are the degrees of membership to four fuzzy subsets of insulation condition respectively, and 28 inputs corresponding to 28 nondestructive parameters of insulation respectively. Secondly, the ANN with fuzzy outputs is trained by the Levenberg-Marquardt fast training algorithm with the goal error of 0.000 1, and the ability of condition evaluation of the network is verified by five 18 kV/300 MW practical stator bars. Finally, the intelligent evaluating software of main insulation based on MATLAB is developed. The research results show that the technique could assess the aging condition of stator bar insulation effectively and accurately.