Name
Abstract | ||
|---|---|---|
Smart sensors are a key driver of Industry 4.0 and can be harnessed to bring about efficiency and ensure quality in manufacturing. Many industrial sensor measurements relate to dynamical systems that evolve over time. It is critical, especially for spatially distributed sensors, to work on a common timescale which could be achieved through traceability to UTC for instance. Sensor data can also be affected by timing errors such as jitter, and noise in the measured signal. Pre-processing the sensor signals can remove these effects of jitter and noise. This paper describes a Bayesian approach for removing the effects of jitter and noise, resulting in an estimate of the true signal along with its associated uncertainty. This pre-processed signal can then be used to make decisions in industrial settings with a degree of confidence dictated by the uncertainty associated with the estimated signal. A Metropolis-Hastings algorithm is used to sample from the posterior distribution of model parameters and inferences are made based on these posterior samples. The Bayesian framework is illustrated on some simulated data. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/MetroInd4.0IoT48571.2020.9138266 | 2020 IEEE International Workshop on Metrology for Industry 4.0 & IoT |
Keywords | DocType | ISBN |
Sensor networks,Industry 4.0,Timing errors,Bayesian Inference,Metropolis-Hastings | Conference | 978-1-7281-4892-2 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kavya Jagan | 1 | 0 | 0.34 |
| Liam Wright | 2 | 0 | 0.34 |
| Peter Harris | 3 | 0 | 0.34 |