ANN-based intelligent pressure sensor in noisy environment

A novel artificial neural network (ANN)-based intelligent capacitive pressure sensor (CPS) in noisy environment is proposed in this paper. A switched capacitor circuit (SCC) is used to convert the change in capacitance of the CPS due to applied pressure into a proportional voltage which is then applied to the ANN model to estimate the pressure. Because of the nonlinear response characteristics of the CPS and its temperature dependence, complex signal processing of the SCC output is required to estimate the applied pressure accurately, especially when the room temperature changes with time, place, or both. The situation becomes further complicated when the CPS encounters random noise, as is the case in many practical situations.

To alleviate these difficulties in estimation of unknown applied pressure in a CPS, a multilayer perceptron (MLP) has been utilized to model the CPS characteristics over a wide temperature range with noise. By training the MLP model suitably, a direct digital readout of the applied pressure can be obtained. From the simulation studies it was verified that the performance of this model is quite satisfactory for a wide variation of temperature, starting from −20°C to 70°C, and for a signal-to-noise ratio (SNR) of 40 dB and above. This modeling technique provides greater flexibility and accuracy in a changing and noisy environment.     

Auto-compensation of nonlinear influence of environmental parameters on the sensor characteristics using neural networks

Usually the environmental parameters influence the sensor characteristics in a nonlinear manner. Therefore obtaining correct readout from a sensor under varying environmental conditions is a complex problem. In this paper we propose a neural network (NN)-based interface framework to automatically compensate for the nonlinear influence of the environmental temperature and the nonlinear-response characteristics of a capacitive pressure sensor (CPS) to provide correct readout. With extensive simulation studies we have shown that the NN-based inverse model of the CPS can estimate the applied pressure with a maximum error of +/- 1.0% for a wide temperature variation from 0 to 250 degrees C. A microcontroller unit-based implementation scheme is also proposed.     

Modeling and development of an ANN-based smart pressure sensor in a dynamic environment

In many engineering applications, a capacitive pressure sensor (CPS) is placed in a dynamic environment in which the temperature variation is quite large. Since the response characteristics of a CPS are highly nonlinear and temperature dependent, in such situations, complex signal processing techniques are needed to obtain correct readout of the applied pressure. We have proposed an artificial neural network (ANN)-based smart capacitive pressure sensor, whose response characteristics can be estimated within an accuracy of ±1% error over a wide variation of temperature starting from −50°C to 150°C. This modeling scheme automatically takes care of all the nonidealities, such as, nonlinearity, offset, gain and temperature dependence, of the sensor. A novel idea of automatic collection of temperature information and its feeding into the ANN model is also proposed. In the practical implementation of this scheme, the hardware complexity poses a serious impairment. Since the tanh() functions are needed for implementation in the ANN-based model, to reduce the hardware requirement, we provide a simple scheme for computation of tanh(). Sensitivity analysis of the model with respect to the finite word-length constraint on the final stored weight values, and number of terms used in the implementation of tanh() function, have been carried out. A microcontroller-based implementation scheme for the ANN-based model is also suggested.     

Auto-calibration and -compensation of a capacitive pressure sensor using multilayer perceptrons

Using multilayer perceptrons (MLPs), a smart model for a capacitive pressure sensor (CPS) is proposed. When the ambient temperature changes, the nonlinear response characteristics of a CPS may vary widely. Under such conditions, calibration of the sensor and compensation of the nonlinear sensor characteristics to obtain correct readout becomes a difficult task. The proposed MLP model can provide automatic nonlinear compensation and calibration of the CPS characteristics. A microcontroller unit (MCU)-based implementation scheme for this model is also considered. Simulation results show that this model can estimate the pressure with a maximum full-scale error of +/- 1% over a variation of temperature from -50 to 150 degrees C.     

Modeling of an intelligent pressure sensor using functional link artificial neural networks

A capacitor pressure sensor (CPS) is modeled for accurate readout of applied pressure using a novel artificial neural network (ANN). The proposed functional link ANN (FLANN) is a computationally efficient nonlinear network and is capable of complex nonlinear mapping between its input and output pattern space. The nonlinearity is introduced into the FLANN by passing the input pattern through a functional expansion unit. Three different polynomials such as, Chebyschev, Legendre and power series have been employed in the FLANN. The FLANN offers computational advantage over a multilayer perceptron (MLP) for similar performance in modeling of the CPS. The prime aim of the present paper is to develop an intelligent model of the CPS involving less computational complexity, so that its implementation can be economical and robust. It is shown that, over a wide temperature variation ranging from -50 to 150 degrees C, the maximum error of estimation of pressure remains within +/- 3%. With the help of computer simulation, the performance of the three types of FLANN models has been compared to that of an MLP based model.     

电容压力传感器的FLANN建模方法

旨在开发一种计算简单的电容压力传感器的模型，以便经济、可靠地应用。分析表明采用新型函数链接型神经网络建立的电容压力传感器模型能够精确读出应用压力，它是一种能实现输入到输出的高度非线性映射并且运算高效的非线性网络，在建立传感器模型的类似性能上比多层感知器具有更高的运算优势。     

Compact and accurate digital thermometer based on Anderson’s loop and Pt-100 sensor

A simple and practical digital thermometer with an accuracy better than 0.1°C over a near-room-temperature (from −10°C to 50°C) measurement range has been developed. The instrument is compact and battery operated and provides for both digital and analog outputs. A four-lead platinum thermal sensor, driven by a constant current loop, allows for accurate temperature readings with high immunity to the contact resistances and to their variations. A low-noise electronics allows for temperature measurements with a 1 mK resolution. By experimentally characterizing the non-linearity of the adopted Pt-100 sensor, a suitable readout correction table has been calculated in order to compensate for the sensor non-linear behavior. This compensating procedure allows for a wider (from −50°C to +200°C) and higher accuracy (0.05°C) measurement range. The ultimate accuracy was essentially limited by the accuracy of the temperature standard used for calibration.     

基于神经网络的气体传感器故障诊断

该文介绍了一种基于人工神经网络进行了气体传感器故障检测的新方法，文中利用单个气体传感器的输出信息为气体传感器建立了动态非线性神经网络气体传感器输出模型，并利用该模型进行在线故障检测，实际使用证明该模型具有良好的收敛性和稳定性，完全能满足对气体传感器故障在线检测的需要。     

电阻应变式传感器在应用中的误差补偿

介绍电阻应变式传感器在应用中由于环境温度等因素的影响,会产生各种误差。传感器在实际测量中采用温度补偿、非线性误差补偿、智能压力传感器补偿的方法来提高测量精度,保证测量的准确性。     

基于SVM构造的FLANN数据融合方法在CPS修正中的应用

在对常规函数链接型神经网络（FLANN）构造方法的认识基础上，讨论了一种基于支持向量机（SVM）技术的FLANN构造新方法，并利用该方法对实际的电容压力传感器（CPS）系统进行非线性修正及温度补偿。先将SVM的拓扑结构与常规FLANN结构进行比较，确定两者的等价性。因此，可通过SVM求解二次规划问题来实现FLANN结构的唯一优化。用常规FLANN方法在同样条件下进行对比实验，实验结果表明用该方法构造的FLANN具有结果唯一、结构简单、全局优化等特点，特别是在实验数据较少的小样本条件下仍然具有更高的鲁棒性和修正精度。     

MEMS压差传感器在小型无人机空速测量中的应用

介绍了一种基于MEMS压差传感器和数字信号处理器(DSP)的小型无人机空速测量系统的实现方法.根据实际需求对压差传感器进行了温度补偿,并采用最小二乘法消除器件和电路的非线性;经实验测试,空速在13～50 m/s范围内,该系统的测量精度在±3％以内.该空速测量系统具有体积小、重量轻、功耗低、工作可靠等优点.     

可穿戴式电子织物仿生皮肤设计与应用研究

为满足电子仿生皮肤的穿戴舒适度,提出了一种电容式柔性织物压力传感器,采用丝网印刷工艺,以织物为柔性基体,炭黑填充型复合弹性电介质和有机硅导电银胶制备柔性压敏触觉单元。介绍了压敏单元的结构设计与感知机理,研究了炭黑含量与温度对织物触觉单元性能的影响,改善了该电子织物的输出线性度与重复性,实现了0~700 k Pa量程范围迟滞误差为5.6%,动态响应时间为89 ms,灵敏度为0.025 36%/KPa,同时,引入温度补偿以提升触觉感知准确性。通过将织物压敏单元应用于足底压力信息的时空分布研究和机械手的软抓取实验,其足底压力分布及触觉感知实验结果表明,该电容式柔性织物压力传感器具有良好的工作稳定性与触觉感知功能,为可穿戴式人工皮肤的研究提供了一种设计方案。     

A bi-material microcantilever temperature sensor based on optical readout

As one of the simplest MEMS sensors, microcantilever can sense temperature faster and more sensitively than traditional thermometers as its small size and low thermal mass. In this paper, an Au/SiNx bi-material microcantilever temperature sensor based on optical readout is presented. The deflection of the cantilever varies with the change of temperature due to the differences in thermal expansion coefficients between gold and silicon nitride. Then, the temperature could be accurately measured by detecting the deflection of the cantilever with optical lever method. By experiments, the theoretical model is verified and the temperature characteristics of the sensor are also determined. With a commercial microcantilever, the temperature resolution of the sensor is tested to be 0.02 K when 25 mm length of optical arm set. By optimizing the microcantilever parameters, the temperature resolution of the sensor could be 0.1 mK. High sensitivity makes it suitable for some special precise temperature measurements.     

时分复用数字闭环电容式微加速度计接口电路

为实现电容式微加速度计的数字输出闭环,设计了一种数字输出闭环ASIC(Application Specific Integrated Circuit)接口电路,以降低电路输出噪声并提高测量量程。对已有的电容式微加速度计ASIC电路进行了改进,分时段在中间极板上加载差分电容读出信号和由脉宽调变(PWM)波控制的反馈信号,然后由控制器实现闭环,利用Sigma Delta调制器实现模数转换。通过分析差分电容读出电路和Sigma Delta调制器的原理和特性,建立了该数字输出闭环电容式微加速度计的模型,进行了系统的设计与仿真。实验结果表明,该数字输出闭环电容式微加速度计的噪声水平为9.6μg/√Hz,量程为±3g。这些结果验证了时分复用方案的可行性和本文所提出模型的正确性。     

A temperature and pressure controlled calibration system for pressure sensors

A data acquisition and experiment control system has been developed to characterize and calibrate prototype pressure sensors capable of operation in a cryogenic environment. The system consists of: a personal computer for acquisition of sensor output voltage, sensor operating parameters, and data processing including numerically derived corrections for sensor thermal offset, sensitivity variations, and thermal errors; an environmental chamber capable of controlling temperature to within 1 °C over a −184 °C to 220 °C range; a pressure standard capable of generating pressures to within 1 part in 100,000 over a 0 to 344.74 kPa range; and a data logger for recording outputs from system multimeters, precision resistance temperature devices, thermocouples, and power supplies. The system utilizes a modified, commercially available interface board to allow the demultiplexing, digitation, and input of remotely multiplexed, pulse amplitude modulated pressure signals from pressure sensor arrays to the PC bus. System software is discussed and includes: sensor data acquisition, algorithms for numerically derived thermal offset and sensitivity correction, and operation of the environmental chamber and pressure standard.     

光电式脉搏传感器及由其组成的血压仪的研制

人体脉搏和血压信号中包含着丰富的生理信息,是临床诊断的重要判据。本文介绍了光电式脉搏传感器的检测原理及其组成脉搏、血压检测仪的设计方案。采用集成式光敏元件和放大器芯片替代传统光敏器件进而实现对脉搏测量。而血压的测量采取较为普遍的KorotKoff原理测量法,利用压力传感器检测人体血压信号,并经过差分放大后,送至TC14433构成的数字血压表显示输出。该设计是光、机、电、计算机一体化测控技术的集中体现,是机电一体化产品改善人们生活和健康水平的代表。它的无创伤检测技术也是未来生物医学工程的重要发展方向。     

基于神经网络模型的传感器非线性校正

讨论了BP神经网络模型在传感器非线性补偿中的应用.给出了相应的补偿方法,即采用两个相同的传感器对同一被测量进行不同的测量,其测量结果作为神经网络模型的输入,经过补偿后的传感器具有线性的输入输出关系.采用递推预报误差算法(PRE)训练神经网络,具有收敛速度快、收敛精度高的特点.以距离传感器为例,将基于BP神经网络的校正方法应用于减少距离传感器的非线性输出误差.实验结果表明,将训练后的神经网络接入距离传感器可以得到线性的输入-输出关系,增加神经网络隐层节点的数目可以提高校正精度.当隐层节点数取为40时,用于距离传感器非线性校正的神经网络模型在训练100步后的误差指数(EI)为9.6×10-6.结果表明:本文提出的基于神经网络模型的传感器非线性校正方法是行之有效的.     

大量程柔性铰六维力传感器静态解耦的研究

为提高大量程六维力传感器的测量精度,提出了一种新型的六维力传感器非线性静态解耦方法,该方法结合混合递阶遗传算法和小波神经网络的优点,采用递阶遗传算法与最小二乘法分别对小波神经网络隐层结构参数以及输出层权值进行优化,再将优化后的小波神经网络模型用于六维力传感器非线性解耦.建立了基于混合递阶遗传算法和优化小波神经网络的六维力传感器非线性解耦模型,设计了基于混合递阶遗传算法的小波神经网络结构及参数优化算法,给出了六维力传感器非线性解耦的具体实现流程.以最新研制的6-UPUR大量程柔性铰六维力传感器为对象进行实验,结果表明,采用该方法六维力传感器的Ⅰ类误差和Ⅱ类误差分别为1.25％和2.59％,比采用BP和RBF神经网络方法的测量精度高.     

非线性不确定系统的鲁棒虚拟传感器重组的设计

主要将非线性滑模观测器和虚拟传感器重组方法相结合,设计了具有鲁棒性的滑模观测器。把线性系统虚拟传感器重组方法推广到非线性,并针对传感器故障设计合适的滑模观测器,使改变后的系统能够等价于原来的非线性不确定系统。数字仿真证明了该方法的有效性,重组后的系统输出可以很好地跟踪正常工作系统输出。     

基于RBF神经网络集成-模糊加权输出的数字温度传感器误差补偿

数字温度传感器存在非线性误差,在高精度测温系统中需要进行误差补偿。提出了一种基于径向基函数神经网络集成-模糊加权输出(RBFNNE-FWO)的数字温度传感器误差补偿方法:首先根据数字温度传感器的误差特征,提取特征阈值,构造三个相互独立的成员RBFNN;考虑到成员网络之间边界误差补偿问题,构建一种RBFNN集成输出权值模糊调节器,获得RBFNN集成输出权值,从而完成数字温度传感器的全量程误差补偿。与多种方法的比较仿真实验表明,这种RBFNNE-FWO方法的性能最佳、各成员网络边界误差最小,补偿后的数字温度传感器误差减少了两个数量级,大大提高了测温准确度。