.png){kind=icon}
返回
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}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
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.
Keyword:
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
期刊
IF:
5.9
论文数:
2.0W
被引数:
5.8W
机构
引用论文
Industrial Artificial Intelligence in Industry 4.0-Systematic Review, Challenges and Outlook工业4.0中的工业人工智能 -- 系统回顾、挑战与展望.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Sampling-Interval-Aware LSTM for Industrial Process Soft Sensing of Dynamic Time Sequences With Irregular Sampling Measurements具有不规则采样测量的工业过程动态时间序列软测量的采样间隔感知LSTMIEEE SENSORS JOURNAL
IEEE SENSORS JOURNALIF4.5
PREAI
分享收藏GAMI-Net: An explainable neural network based on generalized additive models with structured interactionsGami-net: 基于具有结构化交互作用的广义加性模型的可解释神经网络PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent DiagnosisWaveletKernelNet: 一种用于工业智能诊断的可解释的深度神经网络OAAI
OAAI分享收藏
查看更多内容