.png){kind=icon}
Return
Dynamic Soft Sensor Modeling for Time Sequence Data Based on Convolution Filters
.png){kind=icon}
OA
AI
DOI：10.1109/TCST.2020.3045845.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Dynamic responses, measurement noise, and time delays in industrial processes can affect the accuracy of soft sensing models. Our goal is to create a dynamic soft sensor modeling method that is robust to the abovementioned problems. Aiming at time sequence data, a feature extraction-based model is constructed by combining convolution filtering techniques with a backpropagation neural network. In addition, training strategies based on gradient descent are proposed to ensure the efficiency and accuracy of the training process. Convolution parameters are trained with model parameters synchronously without prior knowledge. The performance is verified through simulations and industrial experiments in terms of measurement noise, sensor drifting, and dynamic modeling problems.
Keywords:
Convolution
Training
Data models
Finite impulse response filters
Noise measurement
Predictive models
Feature extraction
Convolution filter
dynamic modeling
feature extraction
neural network
soft sensor (SS)
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.9
Papers:
4.9K
Citations:
1.7W
Organization
Cited Papers
ShareSaveThe effects of poloxamer and sodium alginate mixture (Guardix-SG®) on range of motion after axillary lymph node dissection: A single-center, prospective, randomized, double-blind pilot study.png)
PLOS ONEOAAI
PLOS ONEIF0
OAAIShareSaveCorrelation of Plastic Strain Energy and Acoustic Emission Energy in Reinforced Concrete StructuresOAAI
OAAIShareSaveShareSaveShareSave
View more