PSO算法在3D打印喷头温度传感器非线性特性校正中的应用

将微粒群优化(PSO)算法应用于3D打印喷头温度检测系统的非线性特性校正. 在温度传感器特性无法准确获取的情况下,给出了基于PSO算法和逆模型实现非线性特性的线性化校正的一般实现思路和步骤. 首先对采集到的样本进行特征分析,提炼出温度传感器非线性特性的逆模型,再利用PSO算法对逆模型中未知参数进行优化求解,从而实现了3D打印喷头温度非线性特性的线性化校正. 最后,对3D打印喷头温度检测系统进行了实验研究,对比了逆模型的PSO参数优化求解和Matlab曲线拟合求解的实验结果,验证了本文基于PSO的喷头温度非线性特性的线性化校正方法的可行性,并可以扩展到一般非线性传感器的线性化校正应用中.

Application of PSO Algorithm to Nonlinear Characteristics Correctionof 3D Printing Nozzle Temperature Sensor

In this paper,the Particle Swarm Optimization(PSO)algorithm is applied to nonlinear characteristic adjustment of 3D printing nozzle temperature sensor. On the occasion that the nonlinear characteristic of the sensor is not available,a general method and an implementation procedure for linearization of the nonlinear sensor based on inverse model are proposed in this paper. Firstly,the sample data are obtained and analyzed. Then the inverse model of temperature sensor is given and the parameters in the inverse model are optimized by the PSO. And based on the optimized inverse model,the goal of the linearization of the sensor nonlinear characteristic is realized. At last,the experiments are conducted,and the inverse model of PSO parameters optimization and Matlab curve fitting solution of the experimental results are compared. The results validate the method proposed in this paper effective and it can be generalized to other nonlinear sensor applications.