基于摩擦纳米发电机的车辆踏板运动量化模型

doi:10.3901/JME.2022.17.215

摘要/Abstract

摘要： 针对当前车辆踏板角度传感器结构复杂，对复杂材料的需要以及对外部电源的依赖等问题，提出一种基于扇形单电极滑动模式摩擦纳米发电机(Sector-single electrode sliding mode triboelectric nanogenerator, S-SETENG) 踏板运动量化模型。首先，在单电极滑动模式摩擦纳米发电机(Single electrode sliding mode triboelectric nanogenerator, SETENG)基础上，根据接触面积与开路电压值之间的潜在规律，开发可获取踏板运动信息的S-SETENG。其次，进行模拟驾驶实验，获取自然驾驶状态下的车辆踏板运动数据，包括驾驶模拟器输出的踏板角度数据和S-SETENG输出的电压数据。然后，利用S-SETENG电压数据和车辆踏板角度数据完成踏板运动量化模型的训练。最后，根据模型在测试集上的结果显示，基于门控循环单元网络(Gate recurrent unit, GRU) 加速踏板运动量化模型和基于长短记忆网络(Long-short term memory, LSTM)的制动踏板运动量化模型的表现最佳，决定系数(R²) 的值都超过0.94，证明该方法的准确性和可行性。这不仅在角度测量领域展示了一种新的方法，而且极大地扩展了摩擦纳米发电机作为自供电传感器的适用性。

关键词: 摩擦纳米发电机, 循环神经网络, 车辆踏板运动, 量化模型

Abstract: Aiming at the problem of complex structure, dependence on complex materials and external power supply of vehicle pedal angle sensor. A quantization model of pedal movement based on the fan-shaped sector-single electrode sliding mode triboelectric nanogenerator (S-SETENG) is proposed. First, on the basis of the single electrode sliding mode triboelectric nanogenerator (SETENG), according to the potential law between the contact area and the open circuit voltage value, the S-SETENG that can obtain pedal movement information is developed. Secondly, through the simulated driving experiment, the pedal movement data in the natural driving state is obtained, including the pedal angle data output by the driving simulator and the voltage data output by S-SETENG. Then, using S-SETENG voltage data and vehicle pedal angle data to complete the training of pedal movement quantification model. Finally, according to the results of the prediction models on the test set, the acceleration pedal movement quantization model based on gate recurrent unit (GRU) and the brake pedal movement quantization model based on long-short term memory (LSTM) perform best, and the value of R square(R²) exceeds 0.94, which proves the accuracy and feasibility of this method. This not only presents a new principle in the field of angle measurement but also greatly expands the applicability of TENGs as self-powered sensors.

Key words: triboelectric nanogenerators, recurrent neural network, vehicle pedal movement, quantitative model

中图分类号:

U463

张浩东, 王武宏, 陆逍, 谭海秋, 蒋晓蓓, 石健. 基于摩擦纳米发电机的车辆踏板运动量化模型[J]. 机械工程学报, 2022, 58(17): 215-225.

ZHANG Haodong, WANG Wuhong, LU Xiao, TAN Haiqiu, JIANG Xiaobei, SHI Jian. Quantitative Model of Vehicle Pedal Movement Based on Triboelectric Nanogenerators[J]. Journal of Mechanical Engineering, 2022, 58(17): 215-225.

参考文献

[1] LV Chen，CAO Dongpu，ZHAO Yifan，et al. Analysis of autopilot disengagements occurring during autonomous vehicle testing[J]. IEEE/CAA Journal of Automatica Sinica，2017，5(1)：58-68.
[2] LV Chen，XING Yang，et al. Hybrid-learning-based classification and quantitative inference of driver braking intensity of an electrified vehicle[J]. IEEE Transactions on vehicular technology，2018，67(7)：5718-5729.
[3] LUAN L，EVANS R D，JOKERST N M，et al. Integrated optical sensor in a digital microfluidic platform[J]. IEEE Sensors Journal，2008，8(5)：628-635.
[4] CIMINELLI C，DELL'OLIO F，CAMPANELLA C E，et al. Photonic technologies for angular velocity sensing[J]. Advances in Optics & Photonics，2010，2(2)：370-404.
[5] ZHANG Xiaodong，KANG Longyun，DIAO Weifeng. The principle of the potentiometer and its applications in the vehicle steering[C]//IEEE International Conference on Vehicular Electronics and Safety，2005. IEEE，2005：20-24.
[6] FERRARI V，et al. Capacitive angular-position sensor with electrically floating conductive rotor and measurement redundancy[J]. IEEE transactions on instrumentation and measurement，2006，55(2)：514-520.
[7] ZHANG Z，NI F，DONG Y，et al. A novel absolute angular position sensor based on electromagnetism[J]. Sensors and Actuators A：Physical，2013，194：196-203.
[8] HOANG H V，JEON J W. An efficient approach to correct the signals and generate high-resolution quadrature pulses for magnetic encoders[J]. IEEE Transactions on Industrial Electronics，2011，58(8)：3634-3646.
[9] ZHU G，CHEN J，ZHANG T，et al. Radial-arrayed rotary electrification for high performance triboelectric generator[J]. Nature Communications，2014，5(3)：3426.
[10] YANG W，CHEN J，ZHU G，et al. Harvesting vibration energy by a triple-cantilever based triboelectric nanogenerator[J]. Nano Research：English Version，2013，6(12)：880-886.
[11] YANG W，CHEN J，WEN X，et al. Triboelectrification based motion sensor for human-machine interfacing[J]. ACS Appl Mater Interfaces，2014，6(10)：7479-7484.
[12] YANG J，CHEN J，LIU Y，et al. Triboelectrification-based organic film nanogenerator for acoustic energy harvesting and self-powered active acoustic sensing[J]. ACS Nano，2014，8(3)：2649-2657.
[13] YANG Y，ZHANG H. Simultaneously harvesting mechanical and chemical energies by a hybrid cell for self-powered biosensors and personal electronics[J]. Energy and Environmental Science，2013，6，1744-1749.
[14] YANG Y，ZHANG H，CHEN J，et al. Single-Electrode-Based sliding triboelectric nanogenerator for self-powered displacement vector sensor system[J]. ACS Nano，2013，7(8)：7342-7351.
[15] ZHANG H，YANG Y，SU Y，et al. Triboelectric nanogenerator for harvesting vibration energy in full space and as self-powered acceleration sensor[J]. Advanced Functional Materials，2014，24(10)：1401-1407.
[16] YANG Y，ZHU G，ZHANG H，et al. Triboelectric nanogenerator for harvesting wind energy and as self-powered wind vector sensor system[J]. ACS Nano，2013，7(10)：9461-9468.
[17] YANG Y，ZHANG H，LIN Z H，et al. Human skin based triboelectric nanogenerators for harvesting biomechanical energy and as self-powered active tactile sensor system[J]. ACS Nano，2013，7(10)：9213-9222.
[18] SU Y，ZHU G，YANG W，et al. Triboelectric sensor for self-powered tracking of object motion inside tubing[J]. ACS Nano，2014，8(4)：3843-3850，2014.
[19] LIN Z H，ZHU G，ZHOU Y S，et al. A self-powered triboelectric nanosensor for mercury ion detection[J]. Angewandte Chemie International Edition，2013，52(19)：5065-5069.
[20] ZHANG H，YANG Y，SU Y，et al. Triboelectric nanogenerator as self-powered active sensors for detecting liquid/gaseous water/ethanol[J]. Nano Energy，2013，2(5)：693-701.
[21] WU Y，JING Q，CHEN J，et al. A self‐powered angle measurement sensor based on triboelectric Nanogenerator[J]. Advanced Functional Materials，2015，25(14)：2166-2174.
[22] XU Y，YANG W. Real-Time monitoring system of automobile driver status and intelligent fatigue warning based on triboelectric nanogenerator[J]. ACS Nano，2021 Apr 27; 5 (4)：7271- 7278.
[23] XIE Z，ZENG Z，WANG Y，et al. Novel sweep-type triboelectric nanogenerator utilizing single freewheel for random triggering motion energy harvesting and driver habits monitoring[J]. Nano Energy，2020，68：104360.
[24] WILLIAMS R J，ZIPSER D. A learning slgorithm for continually running fully recurrent neural networks[J]. Neural Computation，1998，1(2)：270-280.
[25] XU Weixin，MIAO Huihui，et al. Multi-Scale convolutional gated recurrent unit networks for tool wear prediction in smart manufacturing[J]. Chinese Journal of Mechanical Engineering，2021，34(1)：53.
[26] HOCHREITER S，SCHMIDHUBER J. Long short-term memory[J]. Neural Computation，1997，9(8)：1735-1780.
[27] 刘阳，郜志英，周晓敏，等. 工业数据驱动下薄板冷轧颤振的LSTM智能预报[J]. 机械工程学报，2020，56(11)：133-143. LIU Yang，GAO Zhiying，ZHOU Xiaomin，et al. Industrial data-driven intelligent forecast for chatter of cold rolling of thin strip with LSTM recurrent neural network[J]. Journal of Mechanical Engineering，2020，56(11)：133-143.
[28] 胡晓松，陈科坪，唐小林，等. 基于机器学习速度预测的并联混合动力车辆能量管理研究[J]. 机械工程学报，2020，56(16)：181-192. HU Xiaosong，CHEN Keping，TANG Xiaolin，et al. Machine learning velocity prediction-based energy management of parallel hybrid electric vehicle[J]. Journal of Mechanical Engineering，2020，56(16)：181-192.
[29] WANG S，ZHAO J，SHAO C，et al. Truck traffic flow prediction based on LSTM and GRU methods with sampled GPS data[J]. IEEE Access，2020，8： 208158-208169.
[30] ZHONG L W. Triboelectric nanogenerators as new energy technology for self-powered systems and as active mechanical and chemical sensors[J]. ACS Nano，2013，7(11)：9533.
[31] ZHANG S，WANG Y，LIU M，et al. Data-based line trip fault prediction in power systems using LSTM networks and SVM[J]. IEEE Access，2017：7675-7686.
[32] CHANG Z，ZHANG Y，CHEN W. Electricity price prediction based on hybrid model of adam optimized LSTM neural network and wavelet transform[J]. Energy，2019，187，115804.