Diesel generator set fault diagnosis and detection device and method based on deep learning

Abstract

The invention discloses a diesel generator set fault diagnosis and detection device and method based on deep learning. The device comprises a frame (1), a loudspeaker (2), a displayer (6), a memory (10), a CPU (11) and a data collection device (18), wherein a deep learning module (24), a self-adaptive integrated strategy module (20), a historical signal database (23) and a fault category expert system bank (19) are contained in the frame (1), the self-adaptive integrated strategy module (20) is provided with an integrated strategy generator (201), the fault category expert system bank (19) isprovided with a fault category database (191), a fault index database (192), a fault marking database (193) and a fault level database (194), the deep learning module (24) comprises a clustering algorithm, and a signal transceiver (5) is arranged at the middle position of the upper end of the frame (1). Therefore, it is more accurate and convenient for people to perform fault diagnosis and state online monitoring on a diesel generated set.

Description

technical field [0001] The invention relates to a device for fault diagnosis and state monitoring of a diesel generator set, in particular to a device and method for fault diagnosis and detection of a diesel generator set based on deep learning, which belongs to the technical field of fault diagnosis and artificial intelligence. Background technique [0002] Diesel generators are the power heart of electric propulsion ships, and are also one of the important power sources for large commercial ships. They play an irreplaceable role in ensuring the long-term stable navigation of ships. When marine diesel generators operate continuously for a long time under complex and changeable sea conditions, they are often prone to various failures due to heavy workload, variable load, frequent switching between paralleling and electrolysis, and being affected by salt-alkali corrosion and high temperature. . The ship is a complex system that sails "independently" at sea. When the diesel g...

AI Technical Summary

Problems solved by technology

[0003] Before the present invention, there were relatively few products or methods for fault diagnosis and condition monitoring of marine diesel generators on the market, and the traditional "post-maintenance", "planned maintenance" and "scheduled maintenance" for land equipment were still used more. "Maintenance" method, but this method is increasingly unsuitable for the needs of modern shipping, because in the event of a sudden failure at sea, the crew cannot be given enough time to repair at sea, and external rescue cannot be in place in time, and this kind of ship It is impossible for large-scale equipment with a long voyage to reverse flight when encountering problems, so the traditional methods are often very inefficient and not intelligent, and in the past, regular maintenance and replacement of parts based on experience were used to estimate the life of parts based on experience. The maintenance method is easy to cause waste and misjudgment, and brings safety hazards, so it cannot meet the needs of the crew for intelligent fault diagnosis and online status monitoring

[0004] In terms of diesel engine health status monitoring devices, Chinese patent CP203069611U discloses an FPGA system-based instantaneous speed online monitoring device for marine diesel engines. The device includes a magnetoelectric speed sensor, an FPGA system and a computer. The free end of the sensor is used to measure the top dead center signal and the crankshaft angle signal respectively, and the output signal of the sensor is transmitted to the FPGA system for processing, and the instantaneous speed of the diesel engine is calculated, and the fault diagnosis is carried out by calculating the instantaneous speed fluctuation rate. The method and device have a single function, and only measure a single indicator of the speed, which is basically for fault diagnosis of small data samples, and cannot work effectively in the environment of massive monitoring and big data, and is not systematic, and cannot realize fault prediction, online status monitoring and The function of health assessment

Images