Closed-loop neural network controlled accelerometer

Gaura, Elena; Rider, Richard; Steele, Nigel

doi:10.1243/0959651001540852

Cited by 4 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Gaura, Rider, and Steele utilized NNs to control an electrostatic accelerometer. 12 Lee et al used NNs for a gas recognition system for porous tin-oxide gas sensors arrays. 13 We present the use of ANNs to model the dynamic response of electromagnetic microactuators, with particular interest in the maximum displacement for a range of burst frequencies and input currents, as well as for different actuation media and mechanical designs.…”

Section: Introductionmentioning

confidence: 99%

Using neural networks to model an electromagnetic-actuated microactuator

Sutanto

Setia

Papania

et al. 2007

J. Micro/Nanolith. MEMS MOEMS

View full text Add to dashboard Cite

We present the use of artificial neural networks ͑ANNs͒ to model an electromagnetic microelectromechanical system ͑MEMS͒ microactuator. It is inherently complex and time consuming to model/ predict the response of an electromagnetic microactuator numerically by finite element analysis, particularly when it is actuated by a pulse of current in media with different properties ͑e.g., air, water, and diluted methanol͒. ANNs are used to model the maximum displacement ͑d max ͒ of the microactuator for a range of burst frequencies ͑f b ͒ and input currents ͑I coil ͒, as well as different mechanical designs and actuation media. The prediction errors of the ANN model in normal and pressurized air are Ͻ13 and Ͻ2%, respectively. The prediction error for the same response in water or 50% diluted methanol in water is Ͻ10%.

show abstract

Section: Introductionmentioning

confidence: 99%

Using neural networks to model an electromagnetic-actuated microactuator

Sutanto

Setia

Papania

et al. 2007

J. Micro/Nanolith. MEMS MOEMS

View full text Add to dashboard Cite

show abstract

“…al. [14,15] have described the successful use of ANNs for the identification and compensation of some commonly found sources of error in micro-machined sensors. It would appear therefore advantageous to attempt using the same techniques for diagnosis purposes, since both compensation and diagnosis are located in a node.…”

Section: Strategies For Handling Sensor Failurementioning

confidence: 99%

The myth and reality of Wireless Sensor Networks : Designing Optimally Redundant Networks

Newman

Gaura

Mount

2006

2006 International Conference on Mechatronics and Automation

View full text Add to dashboard Cite

This paper considers some of the systems level issues concerned with the building of large scale sensing systems composed of autonomous intelligent sensors. The work is motivated by the potential offered by monolithic, integrated, intelligent MEMS sensors. They provide very low cost sensing in a form which may be included in 'smart structures' for example, in which structural diagnostic capability is deeply integrated into the structure itself. Designing and implementing such large sensing systems, however, raises a number of challenges, of which, many are still far from being resolved. Optimal redundancy, the follow on issue of fault management and their strategic consequences on the overall systems design requirements are chosen for discussion here. When considering the above, extended network lifetime is an important goal in the system design process. A 'peer to peer' architecture of autonomous sensors, with no specialised control or processing nodes in the network is taken as the starting point of the discussion. This architecture is often put forward as being suitable for high reliability requirements, as the operation of the systems is not dependent on the operation of a single, specialised resource. Given that reliability generally depends on redundancy within the array an aim is the optimization of the level of redundancy in that array. Optimal redundancy depends on two systems functions. The first is a means by which a sensor in such an array may self detect fault conditions, and the second is the provision of a reliable means of handling these faults. A method of fault detection based on Artificial Neural Networks (ANNs) is described, which allows a sensor to detect whether it is functioning correctly, based on its own signal and that provided by a single neighbouring sensor. Within a decentralised, peer to peer network the identification of a neighbour and the subsequent handling of fault conditions require careful consideration, since, without a centralised controller, such systems are prone to deadlock conditions if the interaction between peers is not designed properly. The paper presents a protocol design for decentralised fault handling, modelled in the pi-calculus, a formalism which would allow the investigation of the dynamic properties of a system at the specification stage, as well as proof of the existence of required safety and liveness properties. Based on autonomous diagnostics, such as those described, and rigorous systems design techniques dependable networks of autonomous intelligent sensors may be designed.Index Terms -Sensor networks, sensor arrays, fault management .

show abstract

Using very large arrays of intelligent sensors

Newman

Gaura

Proceedings 2003 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM 2003)

View full text Add to dashboard Cite

Closed-loop neural network controlled accelerometer

Cited by 4 publications

References 4 publications

Using neural networks to model an electromagnetic-actuated microactuator

Using neural networks to model an electromagnetic-actuated microactuator

The myth and reality of Wireless Sensor Networks : Designing Optimally Redundant Networks

Using very large arrays of intelligent sensors

Contact Info

Product

Resources

About