.png){kind=icon}
Return
Input Factor Selection Based on Interpretable Neural Network for Industrial Virtual Sensing Application
.png){kind=icon}
PRE
AI
DOI：10.1109/TIM.2023.3323006.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deep learning-based models have been diffusely utilized in industrial virtual sensing tasks. However, these models built on neural networks (NNs) are faced with poor interpretability, i.e., they cannot explain why these features are used, why they can improve model performance, and whether they are reliable in building models. In this article, an interpretable NN (INN) based on a generalized additive model (GAM) structure is proposed to build a succinct virtual sensor with selected efficient input factors. The proposed INN is a disentangled model with multiple subnetworks of GAM, and each subnetwork is meant to discover either one main factor or one interactive factor for the output prediction. In this model, both the standalone and the interactive input variables are taken as the original input factor. Meanwhile, the time delays are also considered in the variables, since the time-delay factors commonly exist between the industrial process variables. Through the sparsity constraint learning, the input factor selection can be explained by the importance, and the model performance is also improved with a tight structure. A numerical example and a real industrial case are presented to verify the effectiveness and superiority of the proposed virtual sensor.
Keywords:
Soft sensors
Predictive models
Delay effects
Data models
Additives
Input variables
Feature extraction
Generalized additive model (GAM)
industrial virtual sensing
input factor selection
interpretable neural network (INN)
sparsity constraint learning
Journal
IF:
5.9
Papers:
2.0W
Citations:
5.8W
Organization
Cited Papers
ShareSaveIndustrial Artificial Intelligence in Industry 4.0-Systematic Review, Challenges and Outlook.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAIShareSaveShareSaveSampling-Interval-Aware LSTM for Industrial Process Soft Sensing of Dynamic Time Sequences With Irregular Sampling MeasurementsIEEE SENSORS JOURNAL
IEEE SENSORS JOURNALIF4.5
PREAI
ShareSaveShareSaveGAMI-Net: An explainable neural network based on generalized additive models with structured interactionsPATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSaveShareSave
View more