{
  "id": "2407.13310",
  "version": "v1",
  "published": "2024-07-18T09:13:22.000Z",
  "updated": "2024-07-18T09:13:22.000Z",
  "title": "A deep latent variable model for semi-supervised multi-unit soft sensing in industrial processes",
  "authors": [
    "Bjarne Grimstad",
    "Kristian Løvland",
    "Lars S. Imsland",
    "Vidar Gunnerud"
  ],
  "comment": "30 pages, 11 figures",
  "categories": [
    "stat.ML",
    "cs.LG"
  ],
  "abstract": "In many industrial processes, an apparent lack of data limits the development of data-driven soft sensors. There are, however, often opportunities to learn stronger models by being more data-efficient. To achieve this, one can leverage knowledge about the data from which the soft sensor is learned. Taking advantage of properties frequently possessed by industrial data, we introduce a deep latent variable model for semi-supervised multi-unit soft sensing. This hierarchical, generative model is able to jointly model different units, as well as learning from both labeled and unlabeled data. An empirical study of multi-unit soft sensing is conducted using two datasets: a synthetic dataset of single-phase fluid flow, and a large, real dataset of multi-phase flow in oil and gas wells. We show that by combining semi-supervised and multi-task learning, the proposed model achieves superior results, outperforming current leading methods for this soft sensing problem. We also show that when a model has been trained on a multi-unit dataset, it may be finetuned to previously unseen units using only a handful of data points. In this finetuning procedure, unlabeled data improve soft sensor performance; remarkably, this is true even when no labeled data are available.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-07-18T09:13:22.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep latent variable model",
      "semi-supervised multi-unit soft sensing",
      "industrial processes",
      "soft sensor",
      "model achieves superior results"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 30,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}