Fire control system fault diagnosis method based on KPCA-ISSA-SVM

• Main Authors: WANG DEBIAO, GUO LI'NAN, KUANG BOQI, YIN ZHIPENG, LIU HAIYANG, GAO JINTAO, LI YINGSHUN
• Format: Patent
• Language: Chinese; English
• Published: 24.05.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a fire control system fault diagnosis method based on KPCA-ISSA-SVM, and relates to the technical field of electrical digital data processing.The fire control system fault diagnosis method comprises the steps that pin signals of test elements under different conditions are collected, nonlinear features of fault data are extracted through kernel principal component analysis dimensionality reduction, and the data dimensionality is reduced; chaotic mapping and a nonlinear inertia weight factor are introduced to improve a sparrow search algorithm, and parameter optimization is carried out; inputting parameters obtained after optimization into a support vector machine model to establish a fault diagnosis model; according to the method, the global search capability is enhanced, in the algorithm optimization process, a nonlinear inertia weight factor is introduced to adjust the position of a sparrow individual and update the correlation degree of the position of the sparrow individual, the gl