论文部分内容阅读
提出了一种用于火灾自动探测的神经网络模糊推理系统，它采用前馈神经网络对火灾探测器信号进行处理，神经网络输出的火灾概率经模糊推理系统判决，输出火灾报警信号。这种方法结合了神经网络和模糊逻辑的优点，实验表明这种系统能够准确探测火灾并减少了误报警。
A neural network fuzzy inference system for automatic fire detection is proposed. It uses the feedforward neural network to process the fire detector signal. The fire probability output by the neural network is judged by the fuzzy inference system and the fire alarm signal is output. This approach combines the advantages of neural networks and fuzzy logic. Experiments show that this system can accurately detect fires and reduce false alarms.