Method for establishing sample set and computing equipment

Abstract

The invention discloses a method for establishing a sample set, which is executed in computing equipment and comprises the following steps of: acquiring vibration data and equipment attribute information of one or more pieces of equipment; inputting the vibration data into a pre-training model, processing the vibration data by the pre-training model, and outputting corresponding annotation data; generating to-be-determined samples based on the vibration data and the corresponding annotation data, and generating a to-be-determined sample set based on a plurality of to-be-determined samples; and correcting a plurality of to-be-determined samples in the to-be-determined sample set to generate a target sample set so as to train the pre-training model based on the target sample set. The invention also discloses a corresponding computing device. According to the method for establishing the sample set, a large number of more comprehensive samples can be generated, the generation efficiency of the samples is high, the model trained based on the samples can meet the monitoring requirements of multiple states of the equipment, and the intelligent level of equipment state monitoring can be improved.

Description

technical field [0001] The invention relates to the technical field of intelligent monitoring, in particular to a method and computing equipment for establishing a sample set. Background technique [0002] In the context of big data and artificial intelligence, all walks of life are advancing the degree of intelligence. In the process of studying intelligent algorithms and engineering practice, experimental samples are an important tool for training and evaluating intelligent algorithms, and the scale of experimental samples is even more important than the exquisite design of algorithm models. At present, due to the lack of effective, comprehensive, and a large number of relevant samples reflecting equipment failure status in the field of equipment condition monitoring, the level of intelligence in the field of equipment condition monitoring is still low. [0003] At present, the most common and intelligently developed equipment condition monitoring method is vibration-base...

AI Technical Summary

Problems solved by technology

This scheme has the following defects: the simulated equipment is single, and it is impossible to simulate the operating status of all equipment in industrial sites with various equipment types; the operating conditions of equipment are too simple compared with the operating conditions of real industrial site equipment; the operating status of equipment that can be simulated Relatively simple, it is difficult to obtain the status data of the entire life cycle of the device

The disadvantage of this solution is that at present, the number of monitoring equipment of various manufacturers in the industry is small, and the source of samples is insufficient; the relevant manufacturers in the industry do not have corresponding service teams for equipment status monitoring, and the equipment status tracking and closed loop during the monitoring process are not timely, and it is impossible to know the operation of the equipment in time state, so that it is impossible to combine the operating state of the equipment with the characteristics of the corresponding state data in a timely manner; at present, the samples formed by relevant manufacturers in the industry tend to be biased towards a certain operating state, and the types of samples are not rich enough. Such as bearing defect samples, there are fewer samples created in other links in the equipment status monitoring process, such as collection, alarm, analysis and other related samples that may be involved in the equipment status data collection process (error signal, start and stop, alarm, diagnosis, etc.) , resulting in poor sample comprehensiveness

Images