Fan foundation and tower structure detection method

The invention relates to a fan foundation and tower structure detection method. The method comprises the following steps of acquiring three signals of displacement, inclination angles and vibration through a detection system, extracting characteristic parameters related to a health state of a fan by adopting a time domain and frequency domain analysis method based on the acquired three signals, and further providing a comprehensive detection method based on a support vector machine training model. According to the method, model training is carried out on the basis of positive and negative characteristic samples of fan operation parameters, a trained support vector machine model comprises fan fault information, health information and sensitivity degree information of the characteristic parameters to faults, and a fan foundation and tower detection mode is formed on the basis of all training models. According to the method, the three signals are collected to detect a state of a fan structure, the extracted char