基于混沌和取样积分技术的大型风电增速箱早期故障诊断

针对风力发电机组增速箱早期故障振动信号被噪声调制污染，信噪比低，难以识别问题，根据增速箱振动信号的特点，提出基于混沌和取样积分技术结合的早期故障诊断方法。采用取样积分技术提高混沌振子对增速箱振动故障信号的检测门限，利用混沌振子相图变化及lyapunov指数确定增速箱齿轮啮合频率边频带及三倍频信号状态变化，从而对齿轮早期故障进行判断。通过对某风场1.5WM风力机增速箱实验，证明该方法有效。

Incipient fault diagnosis of large scale wind turbine gearbox based on chaos theory and sampling integral technology

Vibration signals recognition for incipient faults of large scale wind turbine gearbox is difficult because the signals with low SNR are polluted and modulated by background noise. According to the characters of the gearbox vibration signals, the method based on chaos theory and integral technology is presented to detect its incipient fault signals of gearbox. Sampling integral technology is applied to improve the tracking ability of fault signals with lower SNR. The state of sidebands of meshing frequency and its third harmonic signals can be confirmed by the change of chaotic phase and its lyapunov exponents, and then the incipient faults can be diagnosis. The experimental results on 1.5WM wind turbines gearboxes in a wind field justify the method is effective.