Complex equipment health state assessment method

Abstract

The invention discloses a complex equipment health state assessment method, which assesses to-be-assessed data by establishing a complex equipment health state clustering center training model to judge the health level of complex equipment, and fuses normal state data of the complex equipment into a group of reference normal state data. And further calculating characteristic parameters, namely a cross correlation coefficient, a condensation coefficient and a spectral distance index, as three-dimensional characteristic vector coordinates of each group of training data. Performing clustering analysis on the feature vector array to obtain a clustering center training model, calculating a membership degree and an assessment health level of the to-be-assessed data to the clustering center in a normal state according to an Euclidean distance from the to-be-assessed data to the clustering center, then performing sampling mechanism analysis on the to-be-assessed data, judging the accuracy of an assessment result, and obtaining the assessment result of the to-be-assessed data. And meanwhile, the extracted to-be-evaluated data which is evaluated completely and accurately is added into the training data of the complex equipment, so that the accuracy and the stability of subsequent evaluation work are improved.

Description

technical field [0001] The invention relates to the technical field of equipment health management, in particular to a method for evaluating the health state of complex equipment. Background technique [0002] With the change of the form of war, the requirements for the complexity of equipment are getting higher and higher. Complex equipment refers to equipment with complex composition relations, complex behaviors, complex interactions between subsystems of the system and between the system and its environment, and complex energy exchanges. Because of its outstanding functional performance, which affects the success or failure of missions, it has important strategic and tactical value. [0003] As the functional structure of complex equipment becomes more and more complex, the use profile experienced gradually becomes more and more complex. If the multi-dimensional monitoring of complex equipment operation data is realized in the process of use and maintenance, and its healt...

AI Technical Summary

Problems solved by technology

However, using a single mapping function for calculation requires determining the function that matches the specific equipment and the actual situation in advance, and the workload is heavy.

For example, when the normal and faulty states of the equipment are not clearly distinguished in the time domain signal, it is not good to choose the cross-correlation function for health assessment.

Moreover, the single set of reference data selected in the calculation of the traditional reliability function is accidental and cannot fully represent the health status of the equipment, thus reducing the accuracy of the health assessment.

Images