Data Cleaning Model of Mine Wind Speed Sensor Based on LOF-GMM and SGAIN

To improve the quality of mine ventilation wind speed sensor data, a data cleaning model for mine ventilation wind speed sensors based on LOF-GMM and SGAIN is proposed. First, the LOF-GMM algorithm was used to identify wind speed sensor data, cluster the data, and determine the threshold of the local outlier factor, enabling automatic identification of abnormal data and recognition of ventilation fault state information. Abnormal data were then removed to create blank missing points. Finally, wind speed data from the normal operating state of the ventilation system were used to train the SGAIN model to obtain its optimal parameters. The trained SGAIN model was then used to fill in the blank points. The results show that the proposed method can effectively detect abnormal wind speed sensor data and identify ventilation system fault information. In terms of imputation performance, this model outperformed other data imputation models such as GAIN, RF, and DAE. Although the imputation speed was slightly lower than that of the RF and DAE models, considering the high accuracy requirements of mine wind speed data, SGAIN is more suitable for use in the field of mine ventilation.