scholarly journals Machine Learning based Self-sensing the Stiffness of Shape Memory Coil Actuator

2021 ◽  
Author(s):  
Bhagoji B. Sul ◽  
K. Dhanalakshmi
Keyword(s):  
Machine Learning ◽  
Shape Memory ◽  
Electrical Resistance ◽  
Statistical Parameter ◽  
Automated Method ◽  
Displacement Sensors ◽  
Stiffness Characteristic ◽  
Almost All ◽  
And Control ◽  
Intelligent Model

Abstract Self-sensing actuation (SSA) assists in sensing the vital property of the shape memory coil which can be used to monitor and control the actuation. The stiffness characteristic of the shape memory coil is sensed during actuation which plays a significant role in development of Intelligent Robotics in defense systems. The electrical property of shape memory coil such as electrical resistance changes due to martensitic phase transformation which is further used to sense the mechanical properties such as strain, stress, temperature, length, and force. Nowadays electrical properties are used to sense the stiffness of the shape memory coil. As of now, there is no well-established analytical model to predict the stiffness of sensing during actuation accurately. Therefore, Machine Learning (ML) based data-driven intelligent model is proposed in this paper for auto-sensing of the stiffness. The experimental facility has been developed for the collection of data with respect to diverse Joule heating currents. To determine the experimental data values of stiffness and electrical resistance of shape memory coil is a cumbersome task. Hence we have proposed an automated method to predict the stiffness of the shape memory coil using ML methods. The Classical Polynomial and Feedforward Neural Network (FFNN) models are developed for analyzing the stiffness of the shape memory coil. It is found that FFNN model outperforms the other ML based model by attaining 95.2650 % accuracy. The FFNN model is also able to explain almost all the predicted stiffness values which are experimentally recorded. The FVU (Fraction Variance Unexplained) statistical parameter explains the prediction of FFNN with the value of 0.0842. The great advantage of the ML model is to replace two sensors (Force and displacement sensors) with one soft sensor (ML model). It will be useful in the controlling robotics and other devices which require high precision in data generated by the sensors.

Implementation and Investigation of a Compact, Powerful System for Diagnosis and Control of Shape Memory Alloys in Technical Applications

2019 ◽  
Author(s):  
Max Kaiser ◽  
Nils Neblung ◽  
Martin Gurka
Keyword(s):  
Phase Transformation ◽  
Shape Memory Alloys ◽  
Shape Memory ◽  
Electrical Resistance ◽  
Control Strategies ◽  
Memory Systems ◽  
Constant Load ◽  
Resistance Change ◽  
Model Based ◽  
And Control

Abstract In this paper we present the development, implementation and testing of a compact system for diagnosis and control of actuators based on metallic shape memory alloys (SMA). Using NiTi-SMA, very compact, cost-effective and lightweight actuation systems can be realized. In applications where the SMA is activated by internal Joule heating or its condition is diagnosed by the self-sensing of its electrical resistance, an electrical system capable of reliably measuring very small resistance changes (< 1 ohm) without affecting the phase-state of the SMA is required. In addition, the system must offer the possibility to evaluate the nonlinear, hysteresis-afflicted behavior of the SMA and to handle this difficulty, e.g. utilizing a model-based control. This paper presents a simple compact and adaptive system based on a microcontroller that meets these requirements. Detailed functional tests were carried out with the system to establish a correlation between the change in electrical resistance in the range < 200 mOhm and the current strain state of the actuator. For this purpose, a first series of tests was performed, with the SMA wires working against a constant load. In a second tests series, the SMA wires worked against springs of different stiffness. The use of a microcontroller enables simple implementation of different control strategies. The control system for the non-linear resistance change utilizes a fuzzy logic which divides the control algorithm into three regimes. In the regime of the martensitic phase transformation a PI-controller is used. The state of actuators with an absolute electrical resistance < 1 Ohm and a resistance change < 200 mohm associated with the phase transformation can be precisely measured and controlled with an accuracy < 10 mohm. The system can be configured with little effort for different tasks and shape memory systems of different sizes. Furthermore, it is possible to implement more complex control algorithms up to model-based controllers.

Convergence in norming and control of modern wireless technologies electromagnetic fields

2020 ◽  
Vol 60 (9) ◽  
pp. 610-613
Author(s):  
Michail Yu. Maslov ◽  
Yuri M. Spodobaev
Keyword(s):  
Wireless Communication ◽  
Electromagnetic Fields ◽  
Communication Systems ◽  
Communication Technologies ◽  
Telecommunications Industry ◽  
High Tech ◽  
Wireless Technologies ◽  
Almost All ◽  
Network Technologies ◽  
And Control

Telecommunications industry evolution shows the highest rates of transition to high-tech systems and is accompanied by a trend of deep mutual penetration of technologies - convergence. The dominant telecommunication technologies have become wireless communication systems. The widespread use of modern wireless technologies has led to the saturation of the environment with technological electromagnetic fields and the actualization of the problems of protecting the population from them. This fundamental restructuring has led to a uniform dense placement of radiating fragments of network technologies in the mudflow areas. The changed parameters of the emitted fields became the reason for the revision of the regulatory and methodological support of electromagnetic safety. A fragmented structural, functional and parametric analysis of the problem of protecting the population from the technological fields of network technologies revealed uncertainty in the interpretation of real situations, vulnerability, weakness and groundlessness of the methodological basis of sanitary-hygienic approaches. It is shown that this applies to all stages of the electromagnetic examination of the emitting fragments of network technologies. Distrust arises on the part of specialists and the population in not only the system of sanitary-hygienic control, but also the safety of modern network technologies is being called into question. Growing social tensions and radio phobia are everywhere accompanying the development of wireless communication technologies. The basis for solving almost all problems of protecting the population can be the transfer of subjective methods and means of monitoring and sanitary-hygienic control of electromagnetic fields into the field of IT.

Drug policy and control at the international level

2018 ◽  
Author(s):  
Thomas F. Babor ◽  
Jonathan Caulkins ◽  
Benedikt Fischer ◽  
David Foxcroft ◽  
Keith Humphreys ◽  
...  
Keyword(s):  
Low Income ◽  
Low Income Countries ◽  
Drug Control ◽  
Prescription Medications ◽  
Access To Treatment ◽  
Illicit Markets ◽  
Pain Medications ◽  
Almost All ◽  
And Control ◽  
Illicit Trafficking

International drug control efforts are designed to coordinate domestic laws with international activities that regulate or limit the supply of psychoactive substances. These efforts are organized around three main drug control treaties that almost all countries have ratified in order to prevent illicit trafficking and other drug-related crime, while at the same time allowing access to prescription medications. The effects of the system have been evaluated mostly in terms of the ability to eliminate illicit markets and supply. The gross imbalance in world consumption of legal opiates is a pointer to the limited availability of effective pain medications in many low-income countries, with 80% of the world’s population having either no or inadequate access to treatment for moderate or severe pain.

Learning and control

2018 ◽  
Author(s):  
Ivan Herreros
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Brain Function ◽  
Control Strategies ◽  
Learning Problems ◽  
Animal Learning ◽  
Feed Forward Control ◽  
Machine Learning Applications ◽  
And Control

This chapter discusses basic concepts from control theory and machine learning to facilitate a formal understanding of animal learning and motor control. It first distinguishes between feedback and feed-forward control strategies, and later introduces the classification of machine learning applications into supervised, unsupervised, and reinforcement learning problems. Next, it links these concepts with their counterparts in the domain of the psychology of animal learning, highlighting the analogies between supervised learning and classical conditioning, reinforcement learning and operant conditioning, and between unsupervised and perceptual learning. Additionally, it interprets innate and acquired actions from the standpoint of feedback vs anticipatory and adaptive control. Finally, it argues how this framework of translating knowledge between formal and biological disciplines can serve us to not only structure and advance our understanding of brain function but also enrich engineering solutions at the level of robot learning and control with insights coming from biology.

scholarly journals Effect of Integrated Neuromuscular Exercise in Physical Education Class on Health-Related Fitness in Female Children

Healthcare ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 312
Author(s):  
Marijana Sinđić ◽  
Draženka Mačak ◽  
Nikola Todorović ◽  
Bianka Purda ◽  
Maja Batez
Keyword(s):  
Physical Education ◽  
Muscular Fitness ◽  
Female Children ◽  
Before And After ◽  
Health Related ◽  
The Republic ◽  
Almost All ◽  
And Control ◽  
Cardiorespiratory Endurance ◽  
Health Related Fitness

Integrated neuromuscular training (INT) showed benefits for improving fundamental movement skills (FMS). However, the INT health-related fitness (HRF) effects are lacking. The current study aimed to determine the effects of INT implemented during physical education (PE) in a primary school in the Republic of Serbia on HRF in female children. The sample consisted of 72 healthy girls who were divided into the intervention (EG: n = 37; mean ± SD: age = 8.17 ± 0.31) and control (CG: n = 35; age = 8.11 ± 0.31) groups. The EG and CG performed the INT program and traditional PE activities two times per week within the first ~15 min of PE class, respectively. The Fitnessgram battery tests assessed the HRF (body composition, cardiorespiratory endurance, muscular fitness, and flexibility) before and after the program. After eight weeks, the EG significantly reduced all fat measures, while the CG decreased only triceps skinfold but to a smaller extent (F = 5.92, p < 0.02, ŋ2 = 0.09). Both groups significantly improved the performance of almost all muscular fitness tests (curl-ups, trunk lift, push-ups); however, the EG increased the push-ups more than the CG (F = 9.01, p < 0.01, ŋ2 = 0.14). The EG additionally improved the modified pull-ups (F = 14.09, p < 0.01, ŋ2 = 0.19) and flexed arm hang (F = 28.82, p < 0.01, ŋ2 = 0.33) tests. The flexibility and cardiorespiratory endurance of both groups did not significantly change after eight weeks. This approach of exercise showed positive acceptance and relatively good results after only eight weeks.

scholarly journals Machine learning assisted discovery of new thermoset shape memory polymers based on a small training dataset

Polymer ◽  
2021 ◽  
Vol 214 ◽  
pp. 123351
Author(s):  
Cheng Yan ◽  
Xiaming Feng ◽  
Collin Wick ◽  
Andrew Peters ◽  
Guoqiang Li
Keyword(s):  
Machine Learning ◽  
Shape Memory ◽  
Shape Memory Polymers ◽  
Training Dataset

scholarly journals Blockchain Disrupting Fintech and the Banking System

Proceedings ◽  
2021 ◽  
Vol 74 (1) ◽  
pp. 24
Author(s):  
Eduard Alexandru Stoica ◽  
Daria Maria Sitea
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Big Data ◽  
Financial Institutions ◽  
New World ◽  
Great Part ◽  
Banking System ◽  
Daily Activities ◽  
Blockchain Technology ◽  
Almost All

Nowadays society is profoundly changed by technology, velocity and productivity. While individuals are not yet prepared for holographic connection with banks or financial institutions, other innovative technologies have been adopted. Lately, a new world has been launched, personalized and adapted to reality. It has emerged and started to govern almost all daily activities due to the five key elements that are foundations of the technology: machine to machine (M2M), internet of things (IoT), big data, machine learning and artificial intelligence (AI). Competitive innovations are now on the market, helping with the connection between investors and borrowers—notably crowdfunding and peer-to-peer lending. Blockchain technology is now enjoying great popularity. Thus, a great part of the focus of this research paper is on Elrond. The outcomes highlight the relevance of technology in digital finance.

scholarly journals NLOS Multipath Classification of GNSS Signal Correlation Output Using Machine Learning

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2503
Author(s):  
Taro Suzuki ◽  
Yoshiharu Amano
Keyword(s):  
Machine Learning ◽  
Satellite System ◽  
Training Data ◽  
Support Vector ◽  
Positioning Errors ◽  
Automated Method ◽  
Global Navigation Satellite ◽  
Better Than ◽  
Signal Correlation

This paper proposes a method for detecting non-line-of-sight (NLOS) multipath, which causes large positioning errors in a global navigation satellite system (GNSS). We use GNSS signal correlation output, which is the most primitive GNSS signal processing output, to detect NLOS multipath based on machine learning. The shape of the multi-correlator outputs is distorted due to the NLOS multipath. The features of the shape of the multi-correlator are used to discriminate the NLOS multipath. We implement two supervised learning methods, a support vector machine (SVM) and a neural network (NN), and compare their performance. In addition, we also propose an automated method of collecting training data for LOS and NLOS signals of machine learning. The evaluation of the proposed NLOS detection method in an urban environment confirmed that NN was better than SVM, and 97.7% of NLOS signals were correctly discriminated.

Sign in / Sign up

Export Citation Format

Share Document