Sample cleaning method for fan icing prediction model training

The invention relates to the technical field of data processing, in particular to a sample cleaning method for draught fan icing prediction model training, and the method comprises the steps: obtaining a to-be-cleaned sample in the operation process of a draught fan; wherein the to-be-cleaned sample comprises a plurality of factors; determining time sequence coupling among the various factors by adopting a fan icing prediction model; and cleaning the to-be-cleaned sample based on the time sequence coupling among the multiple factors. According to the method, the influence of noise and the like on the sample can be effectively eliminated, and efficient cleaning of sample data is realized. 本发明涉及数据处理技术领域，具体涉及用于风机覆冰预测模型训练的样本清洗方法，该方法包括：获取风机运行过程中的待清洗样本；其中，所述待清洗样本包括多种因素；采用风机覆冰预测模型，确定所述多种因素之间的时序耦合性；基于所述多种因素之间的时序耦合性，对所述待清洗样本进行清洗。该方法能够有效地消除噪声等对样本的影响，实现样本数据的高效清洗。