Industrial equipment anomaly detection method and device, storage medium and terminal

Abstract

The invention discloses an industrial equipment anomaly detection method and device, a storage medium and a terminal. The method comprises the steps of collecting operation data of current to-be-detected industrial equipment in real time; inputting the operation parameters of the to-be-detected industrial equipment into the detection chip to output a detection result of the to-be-detected industrial equipment; wherein the detection chip comprises a weight file corresponding to a pre-trained industrial equipment detection model, and the pre-trained industrial equipment detection model completesmodel training and deployment after parameter configuration through a visual interface; and when the detection result indicates that the to-be-detected current industrial equipment is abnormal, transmitting abnormal information to related departments through an alarm channel for early warning. Therefore, by adopting the embodiment of the invention, the technical threshold of using an artificial intelligence algorithm in intelligent requirements of industrial equipment fault monitoring, health management, fault diagnosis, energy optimization and the like can be reduced, the costs of model research and development, operation and maintenance and management are reduced, and the operation efficiency of the industrial equipment is further improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a method, device, storage medium and terminal for abnormality detection of industrial equipment. Background technique [0002] At present, intelligent automation of factory production has received more and more attention, because intelligent automation can not only improve production efficiency, but also reduce or eliminate serious losses caused by equipment shutdown. Imbalances, imperfections, loose fasteners and other anomalies in machinery and equipment often translate into vibrations, resulting in loss of accuracy and safety concerns. However, in recent years, with the development of machine learning and edge AI algorithms, machine learning and artificial intelligence algorithms have been applied to factory intelligent automation, and the operating status of industrial equipment can be monitored in real time through machine learning and edge AI algorithms. ...

AI Technical Summary

Problems solved by technology

[0003] At present, when traditional machine learning and artificial intelligence algorithms are applied to factory intelligent automation, there are many steps to deploy traditional artificial intelligence algorithms. Machine learning requires manual collection of a large number of data samples for data labeling. The entire process requires personnel participation and frequent operations. Not only It takes up a lot of time, is also inefficient, and there is a certain degree of management confusion. The probability of human error operation increases, thereby reducing the implementation of machine learning and artificial intelligence algorithms in intelligent automation of factory production, resulting in a further reduction in the cost of industrial equipment. operation efficiency

Images