Equipment performance prediction method and device, storage medium and terminal

Abstract

The invention discloses an equipment performance prediction method and device, a storage medium and a terminal. The method comprises the following steps: determining a performance index for evaluating equipment performance; obtaining a plurality of historical performance index sequences from the historical data, calculating a historical p value to obtain a historical p value set, and determining an early warning p value according to the historical p value set; obtaining a to-be-detected performance index sequence from the to-be-detected data, and calculating a to-be-detected p value; comparing the to-be-detected p value with the early warning p value, and predicting equipment performance according to a comparison result; a to-be-detected p value and a historical p value are calculated according to the following steps: intercepting a performance index sequence with a preset length, and dividing the performance index sequence into a first sub-sequence and a second sub-sequence; constructing a statistic capable of representing a mean level difference between the first sub-sequence and the second sub-sequence, wherein the statistic obeys t distribution; and determining a statistic measured value, and calculating a p value capable of reflecting the equipment fault probability. According to the scheme provided by the invention, the equipment performance can be predicted, so that the early warning accuracy is improved.

Description

technical field [0001] The invention relates to the field of electromechanical technology, in particular to a method and device for predicting equipment performance, a storage medium, and a terminal. Background technique [0002] Early warning means that before disasters and other dangers that need to be guarded against occur, according to the laws summarized in the past or the possible precursors obtained from observations, emergency signals are sent to relevant departments to report dangerous situations, so as to avoid hazards in the case of ignorance or insufficient preparation. occurrence, thereby minimizing the loss caused by the hazard. [0003] In the current electromechanical system, the commonly used early warning methods are mainly experience-based overrun early warning methods. This method relies on the experience and knowledge of many people, and is easily affected by a single abnormal point to report false alarms. Moreover, this kind of early warning method is...

AI Technical Summary

Problems solved by technology

[0004] However, due to the shortcomings of the current early warning method, further research is needed on how to early warning

Images