Soft Sensor Development Based on Kernel Dynamic Time Warping and a Relevant Vector Machine for Unequal-length Batch Processes

2021 ◽  
pp. 115223
Author(s):  
Kepeng Qiu ◽  
Jianlin Wang ◽  
Rutong Wang ◽  
Yongqi Guo ◽  
Liqiang Zhao
Keyword(s):  
Dynamic Time Warping ◽  
Soft Sensor ◽  
Batch Processes ◽  
Time Warping ◽  
Sensor Development ◽  
Dynamic Time ◽  
Unequal Length

Clustering of interval-valued time series of unequal length based on improved dynamic time warping

2019 ◽  
Vol 125 ◽  
pp. 293-304 ◽  
Author(s):  
Xiao Wang ◽  
Fusheng Yu ◽  
Witold Pedrycz ◽  
Lian Yu
Keyword(s):  
Time Series ◽  
Dynamic Time Warping ◽  
Time Warping ◽  
Dynamic Time ◽  
Interval Valued ◽  
Unequal Length

scholarly journals Prediction of Batch Processes Runtime Applying Dynamic Time Warping and Survival Analysis

2020 ◽  
pp. 53-61
Author(s):  
Paolo Graniero ◽  
Marco Gärtler
Keyword(s):  
Survival Analysis ◽  
Survival Data ◽  
Dynamic Time Warping ◽  
Computational Cost ◽  
Predictive Performance ◽  
Time Frame ◽  
Batch Processes ◽  
Time Warping ◽  
Dynamic Time ◽  
The One

AbstractBatch runs corresponding to the same recipe usually have different duration. The data collected by the sensors that equip batch production lines reflects this fact: time series with different lengths and unsynchronized events. Dynamic Time Warping (DTW) is an algorithm successfully used, in batch monitoring too, to synchronize and map to a standard time axis two series, an action called alignment. The online alignment of running batches, although interesting, gives no information on the remaining time frame of the batch, such as its total runtime, or time-to-end. We notice that this problem is similar to the one addressed by Survival Analysis (SA), a statistical technique of standard use in clinical studies to model time-to-event data. Machine Learning (ML) algorithms adapted to survival data exist, with increased predictive performance with respect to classical formulations. We apply a SA-ML-based system to the problem of predicting the time-to-end of a running batch, and show a new application of DTW. The information returned by openended DTW can be used to select relevant data samples for the SA-ML system, without negatively affecting the predictive performance and decreasing the computational cost with respect to the same SA-ML system that uses all the data available. We tested the system on a real-world dataset coming from a chemical plant.

Sign in / Sign up

Export Citation Format

Share Document