A robust transfer deep stochastic configuration network for industrial data modeling

A robust transfer deep stochastic configuration network for industrial data modeling is proposed to address challenging problems such as the presence of outliers (or noise) and conditional drift of the data model due to changes in working conditions. Assuming that outliers follow the t-distribution, the maximum a posteriori estimation is employed to evaluate the read-out weights, and the expectation maximization algorithm is used to iteratively optimize the hyperparameters of the distribution. Moreover, the knowledge contained in the data are expressed in the form of the model structure, connection weights and outlier distribution, and a knowledge-data-based robust transfer strategy is developed to offset the impact of insufficient training data on the learning performance of a deep stochastic configuration network with a new working condition. Comparative experiments are carried out using the historical furnace temperature data of a municipal solid waste incineration plant in China. The results show that the proposed method performs more favorably in robust data modeling and mitigates the impact of changes in working conditions on the applicability and accuracy.

• Publication year

  2023

• Venue

  Industrial Artificial Intelligence

• Publication date

  2023-03-14

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1007/s44244-023-00003-5
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Robust stochastic configuration networks for industrial data modelling with Student's-t mixture distribution

  2022cited by this paper
• Deep stochastic configuration networks with optimised model and hyper-parameters

  2022cited by this paper
• Deep stochastic configuration networks with different random sampling strategies

  2022cited by this paper
• Dynamic transfer partial least squares for domain adaptive regression

  2022cited by this paper
• Discriminative transfer feature learning based on robust-centers

  2022cited by this paper
• Performance of soft sensors based on stochastic configuration networks with nonnegative garrote

  2022cited by this paper
• Stochastic configuration network based cascade generalized predictive control of main steam temperature in power plants

  2021cited by this paper
• Prediction of component concentrations in sodium aluminate liquor using stochastic configuration networks

  2020cited by this paper
• Robust adaptation regularization based on within-class scatter for domain adaptation

  2020cited by this paper
• Development of Adversarial Transfer Learning Soft Sensor for Multigrade Processes

  2020cited by this paper
• Stochastic configuration networks with block increments for data modeling in process industries

  2019cited by this paper
• Construction of prediction intervals for carbon residual of crude oil based on deep stochastic configuration networks

  2019cited by this paper
• Review and big data perspectives on robust data mining approaches for industrial process modeling with outliers and missing data

  2018cited by this paper
• Robust stochastic configuration networks with kernel density estimation for uncertain data regression

  2017cited by this paper
• Robust mixture regression model fitting by Laplace distribution

  2014cited by this paper
• Data-driven Soft Sensors in the process industry

  2009cited by this paper
• Stochastic choice of basis functions in adaptive function approximation and the functional-link net

  1995cited by this paper

• Machine Learning Based Dynamic Spatiotemporal Networks and Bioinspired Optimization for Adaptive Data Modelling and Data Analysis

  2025cites this paper
• Modular stochastic configuration network prediction interval for furnace temperature in municipal solid waste incineration

  2024cites this paper
• Multitarget Robust Deep Stochastic Configuration Network Parameter Modeling Method

  2024cites this paper
• Transfer Learning Soft Sensor Modeling Based on 2-D Domain-Adaption Stochastic Configuration Network

  2024cites this paper