论文部分内容阅读
提出了一种基于飞轮转速波动信号结合神经网络进行内燃机失火故障诊断的方法。对电涡流位移传感器拾取的飞轮位移信号直接进行时域采样，通过软件快速处理可以获得足够测量点数和测量精度的内燃机转速波动信号。ＢＰ神经网络以此作为输入向量，可以快速准确地对内燃机失火气缸进行识别和定位。试验结果表明，该方法具有良好的效果和工程实用性，抗噪声干扰能力和工况适应性很强，并能满足实时诊断的要求。
A method based on flywheel speed fluctuation signal combined with neural network for fault diagnosis of internal combustion engine is proposed. The flywheel displacement signal picked up by the eddy current displacement sensor is directly sampled in the time domain, and the speed fluctuation signal of the internal combustion engine with sufficient measurement points and measurement precision can be obtained by software rapid processing. BP neural network as an input vector, you can quickly and accurately identify and locate the engine cylinder fire. The experimental results show that this method has good effect and engineering practicability, strong anti-noise interference ability and adaptability to working conditions, and can meet the requirements of real-time diagnosis.