Neural Networks to Solve Nonlinear Inverse Kinematic Problems

2018 ◽  
pp. 205-227
Author(s):  
Fusaomi Nataga ◽  
Maki K. Habib ◽  
Keigo Watanabe
Keyword(s):  
Neural Networks ◽  
Industrial Robot ◽  
Inverse Kinematic ◽  
Mean Value ◽  
Original Training ◽  
Serial Link ◽  
Kinematic Models ◽  
The Neural Networks ◽  
The Mean ◽  
Number Of Iterations

In making neural networks learn nonlinear relations effectively, it is desired to have appropriate training sets. In the proposed method, after a certain number of iterations, input-output pairs having worse errors are extracted from the original training set and form a new temporary set. From the following iteration, the temporary set is applied to the neural networks instead of the original set. In this case, only pairs with worse errors are used for updating the weights until the mean value of errors decreases to a desired level. Once the learning is conducted using the temporary set, the original set is applied again instead of the temporary set. The effectiveness of the proposed approach is demonstrated through simulations using kinematic models of a leg module with a serial link structure and an industrial robot.

scholarly journals Robust multi-fidelity design of a micro re-entry unmanned space vehicle

2011 ◽  
Vol 225 (11) ◽  
pp. 1195-1209 ◽  
Author(s):  
E Minisci ◽  
M Vasile ◽  
H Liqiang
Keyword(s):  
Neural Networks ◽  
Optimal Control ◽  
Thermal Protection ◽  
Space Vehicle ◽  
Mean Value ◽  
Maximum Heat ◽  
Direct Transcription ◽  
Maximum Heat Flux ◽  
The Neural Networks ◽  
The Mean

This article addresses the preliminary robust design of a small-scale re-entry unmanned space vehicle by means of a hybrid optimization technique. The approach, developed in this article, closely couples an evolutionary multi-objective algorithm with a direct transcription method for optimal control problems. The evolutionary part handles the shape parameters of the vehicle and the uncertain objective functions, while the direct transcription method generates an optimal control profile for the re-entry trajectory. Uncertainties on the aerodynamic forces and characteristics of the thermal protection material are incorporated into the vehicle model, and a Monte-Carlo sampling procedure is used to compute relevant statistical characteristics of the maximum heat flux and internal temperature. Then, the hybrid algorithm searches for geometries that minimize the mean value of the maximum heat flux, the mean value of the maximum internal temperature, and the weighted sum of their variance: the evolutionary part handles the shape parameters of the vehicle and the uncertain functions, while the direct transcription method generates the optimal control profile for the re-entry trajectory of each individual of the population. During the optimization process, artificial neural networks are utilized to approximate the aerodynamic forces required by the optimal control solver. The artificial neural networks are trained and updated by means of a multi-fidelity approach: initially a low-fidelity analytical model, fitted on a waverider type of vehicle, is used to train the neural networks, and through the evolution a mix of analytical and computational fluid dynamic, high-fidelity computations are used to update it. The data obtained by the high-fidelity model progressively become the main source of updates for the neural networks till, near the end of the optimization process, the influence of the data obtained by the analytical model is practically nullified. On the basis of preliminary results, the adopted technique is able to predict achievable performance of the small spacecraft and the requirements in terms of thermal protection materials.

An Efficient Learning of Neural Networks to Acquire Inverse Kinematics Model

2020 ◽  
pp. 203-232
Author(s):  
Fusaomi Nagata ◽  
Maki K. Habib ◽  
Keigo Watanabe
Keyword(s):  
Neural Networks ◽  
Inverse Kinematics ◽  
Industrial Robot ◽  
Training Data ◽  
Serial Link ◽  
Data Set ◽  
Effective Learning ◽  
The Neural Networks ◽  
Efficient Learning ◽  
Time Required

In this chapter, effective learning approach of inverse kinematics using neural networks with efficient weights update ability has been presented for a serial link structure and industrial robot. Generally, in making neural networks learn a relation among multi inputs and outputs, a desired training data set prepared in advance is used. The training data set consists of multiple pairs of input and output vectors. The input layer receives each input vector for forward computation, and it is compared with the yielded vector from the output layer. The time required for the learning process of the neural networks depends on the number of total weights in the neural networks and that of the input-output pairs in the training data set.

scholarly journals Novel Alphabet Deduction Using MATLAB by Neural Networks and Comparison with the Fuzzy Classifier

2021 ◽  
Vol 36 (1) ◽  
pp. 623-628
Author(s):  
Bapatu Siva Kumar Reddy ◽  
P. Vishnu Vardhan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Character Recognition ◽  
Recognition Rate ◽  
Software Tool ◽  
Mean Value ◽  
Fuzzy Classifier ◽  
The Neural Network ◽  
Accuracy Level ◽  
The Neural Networks

Aim: The study aims to identify or recognize the alphabets using neural networks and fuzzy classifier/logic. Methods and materials: Neural network and fuzzy classifier are used for comparing the recognition of characters. For each classifier sample size is 20. Character recognition was developed using MATLAB R2018a, a software tool. The algorithm is again compared with the Fuzzy classifier to know the accuracy level. Results: Performance of both fuzzy classifier and neural networks are calculated by the accuracy value. The mean value of the fuzzy classifier is 82 and the neural network is 77. The recognition rate (accuracy) with the data features is found to be 98.06%. Fuzzy classifier shows higher significant value of P=0.002 < P=0.005 than the neural networks in recognition of characters. Conclusion: The independent tests for this study shows a higher accuracy level of alphabetical character recognition for Fuzzy classifier when compared with neural networks. Henceforth, the fuzzy classifier shows higher significant than the neural networks in recognition of characters.

scholarly journals Analysis of Open Architecture 6R Robot Forward and Inverse Kinematics Adaptive to Structural Variations

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Chong Wang ◽  
Dongxue Liu ◽  
Qun Sun ◽  
Tong Wang
Keyword(s):  
Inverse Kinematics ◽  
Industrial Robot ◽  
Kinematic Model ◽  
Inverse Kinematic ◽  
Open Architecture ◽  
Model Parameters ◽  
Structural Variations ◽  
Robot Controller ◽  
Kinematic Models ◽  
Kinematic Studies

This paper presents a kinematic analysis for an open architecture 6R robot controller, which is designed to control robots made by domestic manufactures with structural variations. Usually, robot kinematic studies are often introduced for specific robot types, and therefore, difficult to apply the kinematic model from one to another robot. This study incorporates most of the robot structural variations in one model so that it is convenient to switch robot types by modifying model parameters. By combining an adequate set of parameters, the kinematic models, especially the inverse kinematics, are derived. The kinematic models are proved to be suitable for many classic industrial robot types, such as Puma560, ABB IRB120/1600, KAWASAKI RS003N/RS010N, FANUC M6iB/M10iA, and therefore be applicable to those with similar structures. The analysis and derivation of the forward and inverse kinematic models are presented, and the results are proven to be accurate.

scholarly journals A Data-Driven Method for Vehicle Speed Estimation

2021 ◽  
Vol 23 (3) ◽  
pp. B165-B177
Author(s):  
Angelo Bonfitto ◽  
Stefano Feraco
Keyword(s):  
Neural Networks ◽  
Estimation Method ◽  
Mean Value ◽  
Estimation Accuracy ◽  
Speed Estimation ◽  
Vehicle Speed ◽  
The Road ◽  
Computing Platform ◽  
Road Condition ◽  
The Mean

This paper presents a method based on Artificial Neural Networks for estimation of the vehicle speed. The technique exploits the combination of two tasks: a) speed estimation by means of regression neural networks dedicated to different road conditions (dry, wet and icy); b) identification of the road condition with a pattern recognition neural network. The training of the networks is conducted with experimental datasets recorded during the driving sessions performed with a vehicle on different tracks. The effectiveness of the proposed approach is validated experimentally on the same car by deploying the algorithm on a dSPACE computing platform. The estimation accuracy is evaluated by comparing the obtained results to the measurement of an optical sensor installed on the vehicle and to the output of another estimation method, based on the mean value of velocity of the four wheels.

Long-period modulated superstructures in Pd-12.5 at.%Ce and Pd-15 at.%Ce alloys

1990 ◽  
Vol 48 (4) ◽  
pp. 164-165
Author(s):  
Noriyuki Kuwano ◽  
Masaru Itakura ◽  
Kensuke Oki
Keyword(s):  
Electron Microscopy ◽  
Mean Value ◽  
Heavy Elements ◽  
Arc Furnace ◽  
X Ray ◽  
Long Period ◽  
Ultra High Purity ◽  
Heat Treated ◽  
Atomic Scattering ◽  
The Mean

Pd-Ce alloys exhibit various anomalies in physical properties due to mixed valences of Ce, and the anomalies are thought to be strongly related with the crystal structures. Since Pd and Ce are both heavy elements, relative magnitudes of (fcc-fpd) are so small compared with <f> that superlattice reflections, even if any, sometimes cannot be detected in conventional x-ray powder patterns, where fee and fpd are atomic scattering factors of Ce and Pd, and <f> the mean value in the crystal. However, superlattices in Pd-Ce alloys can be analyzed by electron microscopy, thanks to the high detectability of electron diffraction. In this work, we investigated modulated superstructures in alloys with 12.5 and 15.0 at.%Ce.Ingots of Pd-Ce alloys were prepared in an arc furnace under atmosphere of ultra high purity argon. The disc specimens cut out from the ingots were heat-treated in vacuum and electrothinned to electron transparency by a jet method.

Partition Coefficient Ratios and Tumour Perfusion Studied with 85mKr and 133Xe

1987 ◽  
Vol 26 (06) ◽  
pp. 253-257
Author(s):  
M. Mäntylä ◽  
J. Perkkiö ◽  
J. Heikkonen
Keyword(s):  
Partition Coefficient ◽  
Partition Coefficients ◽  
Regional Blood Flow ◽  
Blood Perfusion ◽  
Compartmental Analysis ◽  
Malignant Tumour ◽  
Mean Value ◽  
Perfusion Rate ◽  
Biological Variables ◽  
The Mean

The relative partition coefficients of krypton and xenon, and the regional blood flow in 27 superficial malignant tumour nodules in 22 patients with diagnosed tumours were measured using the 85mKr- and 133Xe-clearance method. In order to minimize the effect of biological variables on the measurements the radionuclides were injected simultaneously into the tumour. The distribution of the radiotracers was assumed to be in equilibrium at the beginning of the experiment. The blood perfusion was calculated by fitting a two-exponential function to the measuring points. The mean value of the perfusion rate calculated from the xenon results was 13 ± 10 ml/(100 g-min) [range 3 to 38 ml/(100 g-min)] and from the krypton results 19 ± 11 ml/(100 g-min) [range 5 to 45 ml/(100 g-min)]. These values were obtained, if the partition coefficients are equal to one. The equations obtained by using compartmental analysis were used for the calculation of the relative partition coefficient of krypton and xenon. The partition coefficient of krypton was found to be slightly smaller than that of xenon, which may be due to its smaller molecular weight.

Detection of Soluble Fibrin Monomer Complexes in Blood by Means of Protamine Sulphate Test

1968 ◽  
Vol 20 (01/02) ◽  
pp. 044-049 ◽  
Author(s):  
B Lipiński ◽  
K Worowski
Keyword(s):  
Human Subjects ◽  
Coronary Thrombosis ◽  
Mean Value ◽  
Healthy Human ◽  
Protamine Sulphate ◽  
Soluble Fibrin ◽  
Fibrin Monomer ◽  
Dog Plasma ◽  
The Mean ◽  
Precipitable Protein

SummaryIn the present paper described is a simple test for detecting soluble fibrin monomer complexes (SFMC) in blood. The test consists in mixing 1% protamine sulphate with diluted oxalated plasma or serum and reading the optical density at 6190 Å. In experiments with dog plasma, enriched with soluble fibrin complexes, it was shown that OD read in PS test is proportional to the amount of fibrin recovered from the precipitate. It was found that SFMC level in plasma increases in rabbits infused intravenously with thrombin and decreases after injection of plasmin with streptokinase. In both cases PS precipitable protein in serum is elevated indicating enhanced fibrinolysis. In healthy human subjects the mean value of OD readings in plasma and sera were found to be 0.30 and 0.11, while in patients with coronary thrombosis they are 0.64 and 0.05 respectively. The origin of SFMC in circulation under physiological and pathological conditions is discussed.

Detection of Circulating Tissue Factor and Factor VII in a Normal Population

1996 ◽  
Vol 75 (05) ◽  
pp. 772-777 ◽  
Author(s):  
Sybille Albrecht ◽  
Matthias Kotzsch ◽  
Gabriele Siegert ◽  
Thomas Luther ◽  
Heinz Großmann ◽  
...  
Keyword(s):  
Tissue Factor ◽  
Normal Population ◽  
Mean Value ◽  
Factor Vii ◽  
Significant Difference ◽  
Age Dependent ◽  
The Mean ◽  
Highly Correlated ◽  
And Gender

SummaryThe plasma tissue factor (TF) concentration was correlated to factor VII concentration (FVIIag) and factor VII activity (FVIIc) in 498 healthy volunteers ranging in age from 17 to 64 years. Immunoassays using monoclonal antibodies (mAbs) were developed for the determination of TF and FVIIag in plasma. The mAbs and the test systems were characterized. The mean value of the TF concentration was 172 ± 135 pg/ml. TF showed no age- and gender-related differences. For the total population, FVIIc, determined by a clotting test, was 110 ± 15% and the factor VIlag was 0.77 ± 0.19 μg/ml. FVII activity was significantly increased with age, whereas the concentration demonstrated no correlation to age in this population. FVII concentration is highly correlated with the activity as measured by clotting assay using rabbit thromboplastin. The ratio between FVIIc and FVIIag was not age-dependent, but demonstrated a significant difference between men and women. Between TF and FVII we could not detect a correlation.

Sign in / Sign up

Export Citation Format

Share Document