Extending Velocity Sensor Bandwidth by Compensating Temperature Dependency Based on BP Neural Network

A compensation method for a magnetoelectric velocity sensor (MVS) is always necessary, which can lower the resonance frequency of the measuring system and subsequently extend the measuring bandwidth. In this paper, a novel compensation method is proposed based on the BP neural network under the TensorFlow architecture. Comparing with the existing methods, the new method does not depend upon an accurate model of the MVS any more, whose parameters are badly influenced by the temperature. The dynamic compensator is connected with the sensor. The BP neural network algorithm is used to identify compensation parameters. The dynamic compensator works at state of the optimum parameter all the time to compensate the dynamic performance of MVS by training the weights and thresholds of the neural network. The experiment results show that velocity measurement deviation is within ±5% error band by the dynamic compensator, which can reduce the measurement deviation caused by the variation of temperature and improve the measurement accuracy. The bandwidth can be as low as 0.28Hz. The dynamic compensator is superior to Random Forests and RBF Neutral Network in implement in FPGA/CPLD. Its’ accuracy is superior to zero-pole compensation method. This method leads a new way to weaken the temperature variation characteristics of the velocity sensor and improve the measurement performance.

[1]  Sheng Zhang,et al.  A family of robust adaptive filtering algorithms based on sigmoid cost , 2018, Signal Process..

[2]  Satoshi Fujita,et al.  Semiconductor ceramics having negative temperature coefficient of resistance and thermistor having a negative temperature coefficient , 2001 .

[3]  Neven Alujević,et al.  Passive and active vibration isolation systems using inerter , 2018 .

[4]  Shiyuan Wang,et al.  Robust least mean logarithmic square adaptive filtering algorithms , 2019, J. Frankl. Inst..

[5]  Qinghua Zhang,et al.  Adaptive Kalman filter for actuator fault diagnosis , 2017, Autom..

[6]  Xin Yang,et al.  Heading Control of Unmanned Marine Vehicles Based on an Improved Robust Adaptive Fuzzy Neural Network Control Algorithm , 2019, IEEE Access.

[7]  Fang Fang,et al.  An ATPSO-BP neural network modeling and its application in mechanical property prediction , 2019, Computational Materials Science.

[8]  Bintang Yang,et al.  A new angular velocity sensor with ultrahigh resolution using magnetoelectric effect under the principle of Coriolis force , 2016 .

[9]  Gao Feng,et al.  Low-frequency characteristics extension for vibration sensors , 2004 .

[10]  Neil M. White,et al.  Application of analog adaptive filters for dynamic sensor compensation , 2005, IEEE Transactions on Instrumentation and Measurement.

[11]  Elena A. Lomonova,et al.  Modeling of an electromagnetic geophone with passive magnetic spring , 2009 .

[12]  Mohamed Djendi,et al.  A new adaptive filtering algorithm for stereophonic acoustic echo cancellation , 2019, Applied Acoustics.

[13]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[14]  Massimo Di Pierro,et al.  Improving trading technical analysis with TensorFlow Long Short-Term Memory (LSTM) Neural Network , 2019, The Journal of Finance and Data Science.

[15]  Johannes A.G.M. van Dijk,et al.  Two-sensor control in active vibration isolation using hard mounts , 2014 .

[16]  Hans Butler,et al.  Position Control in Lithographic Equipment [Applications of Control] , 2011, IEEE Control Systems.

[17]  Makoto Ishida,et al.  Compensation Method Of Offset And Its Temperature Drift In Silicon Piezoresistive Pressure Sensor Using Double Wheatstone-bridge Configuration , 1995, Proceedings of the International Solid-State Sensors and Actuators Conference - TRANSDUCERS '95.

[18]  Yuming Ma,et al.  Compensation of automatic weighing error of belt weigher based on BP neural network , 2018, Measurement.

[19]  Georg Schitter,et al.  Atomic force microscopy using voice coil actuators for vibration isolation , 2015, 2015 IEEE International Conference on Advanced Intelligent Mechatronics (AIM).

[20]  Redha M. Radaydeh,et al.  FPGA-Based Hardware Implementation of Computationally Efficient Multi-Source DOA Estimation Algorithms , 2019, IEEE Access.

[21]  Kezhu Song,et al.  An electromagnetic feedback method to improve low-frequency response performance of geophone , 2016, 2016 IEEE SENSORS.

[22]  Kai Song,et al.  Temperature and Humidity Compensation for MOS Gas Sensor Based on Random Forests , 2017, LSMS/ICSEE.

[23]  Ding-Xuan Zhou,et al.  Universality of Deep Convolutional Neural Networks , 2018, Applied and Computational Harmonic Analysis.

[24]  Yuanli Cai,et al.  A Fuzzy Model Predictive Control Based Upon Adaptive Neural Network Disturbance Observer for a Constrained Hypersonic Vehicle , 2018, IEEE Access.

[25]  Wei-Lung Mao,et al.  Recursive Particle Filter-Based RBF Network on Time Series Prediction of Measurement Data , 2018, Neural Processing Letters.

[26]  Xiaowei Shao,et al.  Kalman filtering through the feedback adaption of prior error covariance , 2018, Signal Process..

[27]  Thuong Le-Tien,et al.  FPGA Platform applied for Facial Expression Recognition System using Convolutional Neural Networks , 2019, ANT/EDI40.

[28]  Andrew J. Fleming,et al.  Optimal integral force feedback for active vibration control , 2015 .