Fault classification method for coal pulverizing system of thermal power plant

• Main Authors: DAI XUAN, XIAO XIANYI, ZHANG YAFEI, GUO FENG, XU ZHENYUAN, CHENG DAZHI, JIN QUAN, LIANG CHUANLONG
• Format: Patent
• Language: Chinese; English
• Published: 31.10.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention provides a fault classification method for a coal pulverizing system of a thermal power plant. The fault classification method comprises the following steps: S1, information collection: collecting real-time data and historical receipts; s2, setting a standard library: setting the standard library according to experimental data of equipment and experience average data in production; s3, the data processing center carries out comparison processing on the data obtained in S1 and S2 to obtain a fault data list, S4, the obtained fault data set is sequentially input into the BERT deep learning network for model training, verification and testing, multiple trained BERT convolutional neural network models are correspondingly obtained, two modified materials are newly provided by clients, and different from the original materials, the two modified materials are different from the original materials. And if not, classifying the input system prompt information data by using the cascade network to obtain a