然核函数的存在会增强模型结构的稳定性，但同时会导致KELM对核参数K和

Although the existence of the kernel function will enhance the stability of the model structure, it will also cause KELM to be very sensitive to the settings of the kernel parameter K and the penalty parameter C. In order to avoid the fluctuation of network structure caused by random assignment, this paper proposes an OLTC fault diagnosis method based on an improved algorithm to optimize the core extreme learning machine.

However, the existence of kernel function will enhance the stability of the model structure, but at the same time, kelm will be very sensitive to the setting of kernel parameter K and penalty parameter C. In order to avoid the fluctuation of network structure caused by random assignment, an OLTC fault diagnosis method based on improved algorithm optimization kernel limit learning machine is proposed in this paper.<br>

However, the existence of kernel function will enhance the stability of the model structure, but at the same time, it will cause KELM to be very sensitive to the setting of kernel parameter k and penalty parameter c. In order to avoid the fluctuation of network structure caused by random assignment, this paper proposes an OLTC fault diagnosis method based on an improved algorithm to optimize the kernel extreme learning machine.