Motor monitoring system based on machine learning

Abstract

The present invention provides a motor monitoring system based on machine learning. The system comprises a data obtaining layer, a data transmission layer, an industrial cloud platform and an application layer. The data obtaining layer is mainly physical device for data collection; the data transmission layer employs the Ethernet or Wi-Fi to perform data transmission and uploads the data to the industrial cloud platform through a gateway; the industrial cloud platform is formed by a physical resource layer, a resource management layer, a service layer and a data processing layer; the application layer comprises device monitoring, fault diagnosis, fault prediction and life cycle prediction. The motor monitoring system obtains data of the motor in real time and performs processing, generatesa motor operation mode self-learning dynamic model to provide support for improving the technologies of the motor such as fault diagnosis and prediction, and the system structure can be extended to achieve multi-device monitoring and accurate monitoring of the device.

Description

technical field [0001] The invention relates to a motor monitoring system based on machine learning, which is mainly used in fault detection, accurate diagnosis and predictive maintenance of industrial equipment. Background technique [0002] With the development of modern industry and the continuous integration of "informatization" and "industrialization", whether industrial equipment can operate safely and reliably in the best state is very important for ensuring product quality, improving production capacity, and ensuring production safety. the meaning of [1][2] . The failure of manufacturing equipment refers to the condition that the equipment loses the specified function within the specified time and under the specified conditions. Usually, this failure is caused by the failure of a certain component [3] . [0003] With the complex structure of modern equipment, its influence and role in industrial production are also increasing. The damage of equipment requires a lo...

AI Technical Summary

Problems solved by technology

[0005] The mathematical dynamic model of the three-phase asynchronous motor is a multivariable, nonlinear, strongly coupled and high-order system, and the problems involved in the professional field are difficult and difficult to understand

And this method also requires professional knowledge, and it is necessary to understand the fault pointed to by the waveform or graphic comparison [6]

Moreover, in the above methods, most of them are to limit the running state of the motor, and judge the situation of the motor in a certain state

[0007] In the above-mentioned background technology, the mathematical model of the motor is high-order and complex, and there is a lack of accurate positioning of motor faults in actual production

Images