Diesel engine crankshaft bearing fault diagnosis method based on FEEMD-PE-PNN

• Main Authors: GUO LI'NAN, KUANG BOQI, YIN ZHIPENG, ZHAO YUXIN, AN LIHUA, GUO ZHANNAN, SHI LIN, LI YINGSHUN
• Format: Patent
• Language: Chinese; English
• Published: 02.07.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MEASURING; PHYSICS; TESTING; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR

The invention provides a diesel engine crankshaft bearing fault diagnosis method based on FEEMD-PE-PNN, and belongs to the technical field of diesel engine fault diagnosis, and the method comprises the following steps: S01, obtaining a diesel engine vibration signal; s02, decomposing the obtained diesel engine vibration signal by using fast ensemble empirical mode decomposition; s03, extracting decomposed vibration signal features by adopting permutation entropy; step S04, constructing a probabilistic neural network; s05, optimizing the constructed probabilistic neural network by adopting a frost ice optimization algorithm; and step S06, training a data set by using the optimized probabilistic neural network, and classifying and identifying faults. According to the method, the diesel engine vibration signals are obtained through fast ensemble empirical mode decomposition, the anti-noise capacity is improved, the decomposed vibration signal features are extracted through permutation entropy, and the vibration