Composite Fire Detection System Using Sparse Representation Method. (11th December 2017)

• Record Type: Journal Article
• Authors: Qu, Na; Wang, Jianhui; Liu, Jinhai; Li, Zhonghai
• Other Names: Lay-Ekuakille Aimé Academic Editor.
• Is Part Of: Mathematical problems in engineering. Volume 2017(2017)
• Publication Date: 2017-12-11
• Subjects: Engineering mathematics -- Periodicals; 510.2462
• DOI: 10.1155/2017/6784764
• Languages: English
• ISSNs: 1024-123X

Abstract

Abstract : This paper proposes that fire parameter data of smoke, temperature, and CO is fused by sparse representation algorithm. It designs a kind of overcomplete dictionary and obtains the sparse solution of fire recognition through L 1 norm, L 3 / 4 norm, L 1 / 2 norm, and L 1 / 4 norm, respectively, in order to select more suitable norm type. A comprehensive classification method is proposed for fire identification. The simulation results show that L 1 norm and L 3 / 4 norm are used to obtain the solution with remarkable sparsity and high accuracy. The comprehensive classification method is more effective than minimum residual method and sum of weight coefficients method. This paper uses DSP TMS320F28022 as the core chip, TC72 as the temperature sensor, MQ-7 as the CO gas sensor, and MQ-9 as the smoke sensor to design the hardware of fire detection system. Code Composer Studio (CCS) software is used to compile and debug the program. Proteus software is used to load the program into the hardware circuit for joint simulation. The simulation results show that system design is feasible.