Fault diagnosis method, method for building fault diagnosis model, equipment, device and medium

An electronic device, for diagnosing a fluid device, wherein the fluid device comprises a suction end and a discharge end, the electronic device comprising:

• a processor;
• and
• a memory, comprising a non-transitory computer-readable storage medium storing instructions that, when executed by the processor, cause the electronic device to perform operations comprising:
• training a fault diagnosis model with a sample data set, wherein the fault diagnosis model comprises an encoder and a decoder coupled together, wherein each of the encoder and the decoder comprises a plurality of fully connected layers;
• obtaining a data set for diagnosing the fluid device, wherein the data set comprises first characteristic data of the suction end, second characteristic data of the discharge end, and input-output difference data, wherein the input-output difference data represents a difference between the first characteristic data and the second characteristic data;
• inputting the data set to the encoder of the trained fault diagnosis model;
• and
• determining whether the fluid device is in failure based on an output from the decoder of the trained fault diagnosis model.

A non-transitory computer-readable storage medium for diagnosing a fluid device, wherein the fluid device comprises a suction end and a discharge end, the storage medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:

• training a fault diagnosis model with a sample data set, wherein the fault diagnosis model comprises an encoder and a decoder coupled together, wherein each of the encoder and the decoder comprises a plurality of fully connected layers;
• obtaining a data set for diagnosing the fluid device, wherein the data set comprises first characteristic data of the suction end, second characteristic data of the discharge end, and input-output difference data, wherein the input-output difference data represents a difference between the first characteristic data and the second characteristic data;
• inputting the data set to the encoder of the trained fault diagnosis model;
• and determining whether the fluid device is in failure based on an output from the decoder of the trained fault diagnosis model.