A Deep-Learning Based Multi-Modality Sensor Calibration Method for USV

2018 ◽  
Author(s):  
Hao Liu ◽  
Yingjian Liu ◽  
Xiaoyan Gu ◽  
Yingying Wu ◽  
Fangchao Qu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Calibration Method ◽  
Sensor Calibration

Multi-Axial Force/Torque Sensor Calibration Method Based on Deep-Learning

2018 ◽  
Vol 18 (13) ◽  
pp. 5485-5496 ◽  
Author(s):  
Hyun Seok Oh ◽  
Uikyum Kim ◽  
Gitae Kang ◽  
Joon Kyue Seo ◽  
Hyouk Ryeol Choi
Keyword(s):  
Deep Learning ◽  
Axial Force ◽  
Calibration Method ◽  
Sensor Calibration ◽  
Torque Sensor

scholarly journals A Normal Sensor Calibration Method Based on an Extended Kalman Filter for Robotic Drilling

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3485 ◽  
Author(s):  
Dongdong Chen ◽  
Peijiang Yuan ◽  
Tianmiao Wang ◽  
Ying Cai ◽  
Haiyang Tang
Keyword(s):  
Kalman Filter ◽  
Laser Beam ◽  
Extended Kalman Filter ◽  
Zero Point ◽  
Calibration Method ◽  
Sensor Calibration ◽  
Beam Direction ◽  
Displacement Sensors ◽  
Robotic Drilling ◽  
Drilling System

To enhance the perpendicularity accuracy in the robotic drilling system, a normal sensor calibration method is proposed to identify the errors of the zero point and laser beam direction of laser displacement sensors simultaneously. The procedure of normal adjustment of the robotic drilling system is introduced firstly. Next the measurement model of the zero point and laser beam direction on a datum plane is constructed based on the principle of the distance measurement for laser displacement sensors. An extended Kalman filter algorithm is used to identify the sensor errors. Then the surface normal measurement and attitude adjustments are presented to ensure that the axis of the drill bit coincides with the normal at drilling point. Finally, simulations are conducted to study the performance of the proposed calibration method and experiments are carried out on a robotic drilling system. The simulation and experimental results show that the perpendicularity of the hole is within 0.2°. They also demonstrate that the proposed calibration method has high accuracy of parameter identification and lays a basis for high-precision perpendicularity accuracy of drilling in the robotic drilling system.

scholarly journals Online Calibration Method for Current Sensors Based on GPS

Energies ◽  
2019 ◽  
Vol 12 (10) ◽  
pp. 1923
Author(s):  
Shuang Zhao ◽  
Jun Liu ◽  
Yansong Li
Keyword(s):  
Calibration Method ◽  
National Standard ◽  
Economic Losses ◽  
Current Sensor ◽  
Sensor Calibration ◽  
Gps Receiver ◽  
Angular Difference ◽  
Online Calibration ◽  
Calibration Methods ◽  
Current Sensors

At present, most sensor calibration methods are off-line calibration, which not only makes them time-consuming and laborious, but also causes considerable economic losses. Therefore, in this study, an online calibration method of current sensors is proposed to address the abovementioned issues. The principle and framework of online calibration are introduced. One of the calibration indexes is angular difference. In order to accurately verify it, data acquisition must be precisely synchronized. Therefore, a precise synchronous acquisition system based on GPS timing is proposed. The influence of ionosphere on the accuracy of GPS signal is analyzed and a new method for measuring the inherent delay of GPS receiver is proposed. The synchronous acquisition performance of the system is verified by inter-channel synchronization experiment, and the results show that the synchronization of the system is accurate. Lastly, we apply our online calibration method to the current sensor; the experimental results show that the angular difference and ratio difference meet the requirements of the national standard and the accuracy of the online calibration system can be achieved to 0.2 class, demonstrating the effectiveness of the proposed online calibration method.

The Design of a Multi-Functional Force Loading Device

2014 ◽  
Vol 709 ◽  
pp. 496-499
Author(s):  
Yu Qin Li ◽  
Ying Jun Li ◽  
Huan Yong Cui ◽  
Gui Cong Wang ◽  
Xi Jie Tian
Keyword(s):  
Spatial Information ◽  
Force Sensor ◽  
Calibration Method ◽  
Measurement Range ◽  
Sensor Technology ◽  
Sensor Calibration ◽  
Force Loading ◽  
Technical Performance ◽  
Loading Device ◽  
Simple Measurement

As a mechanical component, sensor can detect spatial information. Sensor technology has been widely used in national defense, aerospace, industrial inspection and automated production areas and so on. However, the sensor calibration device cannot meet the demand of the development of the sensor. In this paper, a multi-functional force loading device, which is of good technical performance, reliable operation, wide measurement range and simple measurement method, and a six-dimensional force sensor calibration method are described.

Research on Calibration Method of Linear Structured Light Vision Measurement System

2014 ◽  
Vol 644-650 ◽  
pp. 1234-1239
Author(s):  
Tao He ◽  
Yu Lang Xie ◽  
Cai Sheng Zhu ◽  
Jiu Yin Chen
Keyword(s):  
High Precision ◽  
Measurement System ◽  
Structured Light ◽  
Target Position ◽  
Calibration Method ◽  
Measurement Model ◽  
Sensor Calibration ◽  
Vision Measurement ◽  
Set Up ◽  
Structured Light Vision

This template explains and demonstrates how to design a measurement system based on the size of the linear structured light vision, the system could works at realized the high precision and fast measurement of the size of mechanical parts, and accurate calibration of the system. First of all, this paper set up the experimental platform based on linear structured light vision measurement. Secondly, this paper established a system of measurement model, and puts forward a new method of calibration of structured light sensor and set up the mathematical model of sensor calibration. This calibration method only need to use some gage blocks of high precision as the target, the target position need not have a strict requirements, and the solving process will be more convenient, much easier to field use and maintenance. Finally, measuring accuracy on the system by gage blocks with high precision is verified, the experiment shows that measurement accuracy within 0.050 mmin the depth of 0-80 - mm range. This system can satisfy the demands of precision testing of most industrial parts .with its simple calibration process and high precision, it is suitable for the structured light vision calibration.

scholarly journals A systematic MEMS sensor calibration framework

2015 ◽  
Vol 4 (1) ◽  
pp. 97-102 ◽  
Author(s):  
A. Dickow ◽  
G. Feiertag
Keyword(s):  
Pressure Sensors ◽  
Calibration Method ◽  
Least Square ◽  
Sensor Data ◽  
Sensor Calibration ◽  
Calibration Point ◽  
Point Sets ◽  
Mems Sensor ◽  
Least Square Fit

Abstract. In this paper we present a systematic method to determine sets of close to optimal sensor calibration points for a polynomial approximation. For each set of calibration points a polynomial is used to fit the nonlinear sensor response to the calibration reference. The polynomial parameters are calculated using ordinary least square fit. To determine the quality of each calibration, reference sensor data is measured at discrete test conditions. As an error indicator for the quality of a calibration the root mean square deviation between the calibration polynomial and the reference measurement is calculated. The calibration polynomials and the error indicators are calculated for all possible calibration point sets. To find close to optimal calibration point sets, the worst 99% of the calibration options are dismissed. This results in a multi-dimensional probability distribution of the probably best calibration point sets. In an experiment, barometric MEMS (micro-electromechanical systems) pressure sensors are calibrated using the proposed calibration method at several temperatures and pressures. The framework is applied to a batch of six of each of the following sensor types: Bosch BMP085, Bosch BMP180, and EPCOS T5400. Results indicate which set of calibration points should be chosen to achieve good calibration results.

scholarly journals A New Deep Learning Calibration Method Enhances Genome-Based Prediction of Continuous Crop Traits

2021 ◽  
Vol 12 ◽  
Author(s):  
Osval A. Montesinos-López ◽  
Abelardo Montesinos-López ◽  
Brandon A. Mosqueda-González ◽  
Alison R. Bentley ◽  
Morten Lillemo ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Plant Breeding ◽  
Deep Neural Networks ◽  
Reference Population ◽  
Calibration Method ◽  
Data Sets ◽  
Simple Method ◽  
Continuous Response ◽  
Predicting Performance

Genomic selection (GS) has the potential to revolutionize predictive plant breeding. A reference population is phenotyped and genotyped to train a statistical model that is used to perform genome-enabled predictions of new individuals that were only genotyped. In this vein, deep neural networks, are a type of machine learning model and have been widely adopted for use in GS studies, as they are not parametric methods, making them more adept at capturing nonlinear patterns. However, the training process for deep neural networks is very challenging due to the numerous hyper-parameters that need to be tuned, especially when imperfect tuning can result in biased predictions. In this paper we propose a simple method for calibrating (adjusting) the prediction of continuous response variables resulting from deep learning applications. We evaluated the proposed deep learning calibration method (DL_M2) using four crop breeding data sets and its performance was compared with the standard deep learning method (DL_M1), as well as the standard genomic Best Linear Unbiased Predictor (GBLUP). While the GBLUP was the most accurate model overall, the proposed deep learning calibration method (DL_M2) helped increase the genome-enabled prediction performance in all data sets when compared with the traditional DL method (DL_M1). Taken together, we provide evidence for extending the use of the proposed calibration method to evaluate its potential and consistency for predicting performance in the context of GS applied to plant breeding.

Sign in / Sign up

Export Citation Format

Share Document