Fan gearbox bearing fault early warning method based on LSTM network

• Main Authors: GAO DELAN, SHI RUXIN, CAO QINGCAI, WANG JUAN, TADAO, ZHANG JIANXIN, LIU XIANRONG, TANG HONGFEN, CAO SHANQIAO, ZHANG SHUXIANG, XUN JIAMENG, ZHANG SHUXIAO, XU ZHIXUAN, GUO XUFENG, ZHANG LIXING
• Format: Patent
• Language: Chinese; English
• Published: 17.05.2022
• Subjects: BLASTING; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HEATING; LIGHTING; MACHINES OR ENGINES FOR LIQUIDS; MEASURING; MEASURING QUANTITY OF HEAT; MEASURING TEMPERATURE; MECHANICAL ENGINEERING; OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR; PHYSICS; PRODUCING MECHANICAL POWER; TESTING; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR; WEAPONS; WIND MOTORS; WIND, SPRING WEIGHT AND MISCELLANEOUS MOTORS

The invention discloses a fan gearbox bearing fault early warning method based on an LSTM network, and the method comprises the following steps: 1, enabling probes of a plurality of groups of small temperature sensors to be aligned with a bearing, sensing the temperature of the bearing in real time through the small temperature sensors, and displaying the rotating speed of a fan during working in real time through a display module; 2, when the small temperature sensor senses that the temperature of the bearing is higher than an alarm value set in the small temperature sensor or the display module displays that the rotating speed of the fan is abnormal, the signals are converted into available output signals and transmitted to the single-chip microcomputer control module, the signals are transmitted to the LSTM network learning module through the single-chip microcomputer control module, and the LSTM network learning module is used for learning the temperature of the bearing. The temperature of the bearing is