With the rapid development of the city, all kinds of high-rise buildings, large shopping malls and entertainment places have been built one after another. There are some hidden dangers of fire accidents. Effective prevention and monitoring of fire is the focus of fire prevention and control field. As the information source of fire prevention and control, the preparation of fire detection sensor with high sensitivity and short response time is of great significance for fire prevention and monitoring. At present, the commonly used fire detection sensors mainly include CO sensor, temperature sensor and flame sensor. The sensors detect the characteristic parameters in the fire environment and converts non-electric signals such as gas, temperature, and flame light into electric signals to achieve the purpose of fire warning. With the development of material technology in recent years, especially the development of Carbon Nanotube (CNT) technology, a new fire detection sensor represented by CNT materials has emerged. In this paper, the research progress of CNTs in fire detection sensors is reviewed. The applications of CNTs in CO detection, flame light detection and temperature detection are discussed in detail. Finally, the development trend of fire detection sensors based on CNTs is proposed, and the development direction of fire detection sensors in the Internet of things is prospected.

High-sensitivity early fire detection is an essential prerequisite to intelligent building safety. However, due to the small changes and erratic fluctuations in environmental parameters in the initial combustion phase, it is always a challenging task. To address this challenge, this paper proposes a hybrid feature fusion-based high-sensitivity early fire detection and warning method for in-building environments. More specifically, the temperature, smoke concentration, and carbon monoxide concentration were first selected as the main distinguishing attributes to indicate an in-building fire. Secondly, the propagation neural network (BPNN) and the least squares support vector machine (LSSVM) were employed to achieve the hybrid feature fusion. In addition, the genetic algorithm (GA) and particle swarm optimization (PSO) were also introduced to optimize the BPNN and the LSSVM, respectively. After that, the outputs of the GA-BPNN and the PSO-LSSVM were fused to make a final decision by means of the D-S evidence theory, achieving a highly sensitive and reliable early fire detection and warning system. Finally, an early fire warning system was developed, and the experimental results show that the proposed method can effectively detect an early fire with an accuracy of more than 96% for different types and regions of fire, including polyurethane foam fire, alcohol fire, beech wood smolder, and cotton woven fabric smolder.