基于电涡流传感器的温度位移智能检测方法  被引量:5

Intelligent Detection Method of Temperature and Displacement Based on Eddy Current Sensor

在线阅读下载全文

作  者:张新雨[1,2,3] 王露 宋念龙[1,2,3] 常帅 张东坤[1,2,3] ZHANG Xinyu;WANG Lu;SONG Nianlong;CHANG Shuai;ZHANG Dongkun(National&Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration,Xi'an University of Technology,Xi'an Shaanxi 710048,China;Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing,Xi'an Shaanxi 710048,China;The Faculty of Automation and Information Engineering,Xi'an University of Technology,Xi'an Shaanxi 710048,China)

机构地区:[1]西安理工大学晶体生长设备及系统集成国家地方联合工程研究中心,陕西西安710048 [2]陕西省复杂系统控制与智能信息处理重点实验室,陕西西安710048 [3]西安理工大学自动化与信息工程学院,陕西西安710048

出  处:《传感技术学报》2020年第8期1176-1182,共7页Chinese Journal of Sensors and Actuators

基  金:国家自然科学基金重点项目(61533014);国家自然科学基金项目(61671374,61871318);陕西省自然科学基础研究计划项目(2020JQ-645)。

摘  要:在现有的温度位移检测方法中,绝大部分仅适用于单变量测量,即使有能够同时测量两个变量的方法,测量范围也较窄,无法解决一些高温、腐蚀环境中大范围测量的问题。因此,本文提出了一种基于电涡流传感器的温度位移智能检测方法。首先,基于长短期记忆网络(Long Short Term Memory Networks,LSTM)建立电涡流传感器探头线圈的等效电感L、激励频率f、品质因数Q与被测对象的位移x和温度T的模型,然后利用离线数据对该模型进行训练,再利用训练好的模型对位移x和温度T实现在线测量。最后利用仿真对该温度和位移检测方法的有效性进行验证,实验结果表明,与传统的BP、RBF、MOSVR相比,本文方法可以有效地对被测对象的位移x和温度T实现同时检测,并且优于其他方法。同时本文将该检测方法在单片机系统上进行了实现,以验证其解决实际工程问题的有效性。Most of the existing detection methods of temperature and displacement are only suitable for single-variable measurement.Even if there are a few methods that can measure two variables at the same time,the measurement range is also narrow,which cannot solve some problems of large-scale measurement in high-temperature and corrosive environments.Therefore,this paper proposes an intelligent temperature displacement detection method based on an eddy current sensor.Firstly,based on long short term memory networks(LSTM),the model of the equivalent inductance L,excitation frequency f,and quality factor Q of the eddy current sensor probe coil and the displacement x,temperature T of the measured object is established.Secondly,use offline data to train the model and use the trained model to detect the displacement x and temperature T online.Finally,the effectiveness of the temperature and displacement detection method is verified by simulation.The experimental results show that the proposed method can effectively detect the displacement x and temperature T of the measured object.Compared with the traditional BP,RBF,and MOSVR,the proposed method is superior to other methods.At the same time,this paper implements this method on the single-chip system to verify its effectiveness in solving practical engineering problems.

关 键 词:温度检测 位移检测 电涡流传感器 LSTM 

分 类 号:TP212.12[自动化与计算机技术—检测技术与自动化装置]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象