A multi-condition fault prediction method for complex mechanical equipment

Abstract

The invention relates to a multi-condition fault prediction method for complex mechanical equipment. The method comprises the following steps: (1) establishing a multi-PCA (Principal Component Analysis) model specific to a multi-condition process, and calculating corresponding detection indexes, namely, a T2 statistic and an SPE (Square Prediction Error) for each PCA model; (2) optimizing the two detection indexes of T2 statistic and SPE in each of the PCA models, and performing fault detection on the mechanical equipment to obtain fault data of the mechanical equipment in a transition process; (3) performing fault reconstruction on the fault data of the mechanical equipment in the transition process detected by using the two optimized detection indexes of T2 statistic and SPE to obtain an amplitude estimation value fi for minimizing the reconstructed SPE; (4) performing consistent amplitude estimation on the amplitude estimation values fi obtained after reconstruction of the same fault under different conditions in the transition process; (5) performing trend prediction on the fault amplitude value by using a support vector machine prediction model according to an amplitude estimation value fi obtained after the consistent amplitude estimation. The method can be widely applied to fault prediction of electromechanical equipment.

Description

technical field [0001] The invention relates to a method for predicting failures of mechanical equipment, in particular to a method for predicting failures of complex mechanical equipment under multiple operating conditions. Background technique [0002] With the development of science and technology and industry, mechanical equipment is developing towards large-scale, high-speed and complex. Therefore, the requirements for the reliability, continuity, and economy of equipment and systems are increasing day by day in the production of enterprises. On the basis of effective diagnosis and solutions for equipment and system failures in the past, it is further required that only minor abnormalities occur in the failure When there is a sign, the fault can be predicted and corresponding emergency measures can be put forward. There are various methods of fault prediction, among which statistical process monitoring technology has been developed for more than 20 years and is widely ...

AI Technical Summary

Problems solved by technology

In recent research, the fault estimation method based on Principal Component Analysis (PCA) has been successfully used in fault prediction, but for the data of multi-working condition process, the fault estimation method based on PCA is not very good. Accurate fault prediction. When a complex system operates in multiple working conditions, the relationship between variables will change according to the current working mode of the system. If the system is described according to the data model of a single working condition, it will cause a lot of errors. report and omission

Images