基于PSO-BP算法的隧道窑仿真模型修正方法研究  

Study on Correction Method of Tunnel Kiln Simulation Model Based on PSO-BP Algorithm

作　　者：翁智逸 何非[1] 呼子博 WENG Zhiyi;HE Fei;HU Zibo(School of Mechanical Engineering,Nanjing University of Science and Technology,Nanjing 210094,China;China Arms Industry Information Center,Beijing 100089,China)

机构地区：[1]南京理工大学机械工程学院,江苏南京210094 [2]中国兵器工业信息中心,北京100089

出　　处：《机械制造与自动化》2023年第1期105-109,共5页Machine Building & Automation

基　　金：江苏省军工产品科研生产大数据智能分析及应用军民融合公共服务平台项目(1171061540)。

摘　　要：电热隧道窑广泛应用于压电陶瓷的烧成工艺中,窑内的温度是影响压电陶瓷质量的重要因素。针对电热隧道窑内温度不易被观测,造成其烧成工艺参数优化过程困难的问题,通过数值模拟的方式进行温度场仿真,计算窑炉内部的温度分布;由于在建模分析过程中为消除不确定因素引入了多种假设使计算结果与真实值之间存在较大误差。为了减小误差,基于PSO-BP神经网络算法对初始仿真模型进行修正并进行实验验证。将修正前的模型与实测温度的误差进行对比,结果表明:误差由修正前的8.73%降至修正后的1%以下;修正后的模型可适用于实际生产中的温度检测。Electrothermal tunnel kilns are widely used in the sintering process of piezoelectric ceramics,and the temperature inside the kiln is an important factor affecting the quality of piezoelectric ceramics.To overcome the difficulty in optimization process of sintering parameters due to the difficulty in observing the inner kiln temperature,this paper calculates the temperature distribution inside the kiln by means of numerical simulation based on the actual working conditions.Owing to the introduction of various assumptions in the modeling and analysis process for eliminating uncertainties,there exists a large error between the calculated results and the real values.To reduce the error,the initial simulation model is modified based on the PSO-BP neural network,and experimental verification is conducted.The comparison is made on the calculation results of the corrected simulation model and the initial simulation model,which concludes that the error of the actual measured temperature is reduced from 8.73%before correction to less than 1%after correction,and the corrected model is applicable to actual temperature detection in production.

关 键 词：电热隧道窑 模型修正 不确定性 神经网络算法 

分 类 号：TG155.1[金属学及工艺—热处理]