Trustworthy and Explainable Deep Reinforcement Learning for Safe and Energy-Efficient Process Control: A Use Case in Industrial Compressed Air Systems

• URL: http://arxiv.org/abs/2512.18317v1
• Date: Sat, 20 Dec 2025 11:11:49 GMT
• Title: Trustworthy and Explainable Deep Reinforcement Learning for Safe and Energy-Efficient Process Control: A Use Case in Industrial Compressed Air Systems
• Abstract summary: This paper presents a trustworthy reinforcement learning approach for the control of industrial compressed air systems.<n>We develop a framework that enables safe and energy-efficient operation under realistic boundary conditions.<n>An empirical evaluation shows that the learned policy is physically plausible, anticipates future demand, and consistently respects system boundaries.
• Score: 40.329506465917646
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents a trustworthy reinforcement learning approach for the control of industrial compressed air systems. We develop a framework that enables safe and energy-efficient operation under realistic boundary conditions and introduce a multi-level explainability pipeline combining input perturbation tests, gradient-based sensitivity analysis, and SHAP (SHapley Additive exPlanations) feature attribution. An empirical evaluation across multiple compressor configurations shows that the learned policy is physically plausible, anticipates future demand, and consistently respects system boundaries. Compared to the installed industrial controller, the proposed approach reduces unnecessary overpressure and achieves energy savings of approximately 4\,\% without relying on explicit physics models. The results further indicate that system pressure and forecast information dominate policy decisions, while compressor-level inputs play a secondary role. Overall, the combination of efficiency gains, predictive behavior, and transparent validation supports the trustworthy deployment of reinforcement learning in industrial energy systems.

Related papers

• Safe Reinforcement Learning using Ideas from Model Predictive Control [0.40831821256838124]
  Reinforcement learning enables the synthesis of control policies directly from data.<n>A persistent challenge is ensuring strict, hard safety constraints during the active learning phase.<n>We propose a framework that combines the adaptive, high-performance nature of deep reinforcement learning with the formal safety guarantees of model predictive control.
  arXiv  Detail & Related papers  (2026-07-08T10:35:04Z)
• Learning-Based Robust Control: Unifying Exploration and Distributional Robustness for Reliable Robotics via Free Energy [2.409827426380616]
  Key challenge towards reliable robotic control is devising computational models that can both learn policies and guarantee robustness when deployed in the field.<n>Inspired by the free energy principle in computational neuroscience, we propose a model for policy computation that jointly learns environment dynamics and rewards.
  arXiv  Detail & Related papers  (2026-03-06T19:47:17Z)
• Self-Evolving Multi-Agent Network for Industrial IoT Predictive Maintenance [5.571627005866756]
  Industrial IoT predictive maintenance requires systems capable of real-time anomaly detection without sacrificing interpretability or demanding excessive computational resources.<n>Traditional approaches rely on static, offline-trained models that cannot adapt to evolving operational conditions.<n>We introduce SEMAS, a self-evolving hierarchical multi-agent system that distributes specialized agents across Edge, Fog, and Cloud computational tiers.
  arXiv  Detail & Related papers  (2026-02-17T22:45:43Z)
• Kernel-Based Learning of Safety Barriers [0.9367224590861915]
  Rapid integration of AI algorithms in safety-critical applications is raising concerns about the ability to meet stringent safety standards.<n>Traditional tools for formal safety verification struggle with the black-box nature of AI-driven systems.<n>We present a data-driven approach for safety verification and synthesis of black-box systems with discrete-time dynamics.
  arXiv  Detail & Related papers  (2026-01-17T10:42:35Z)
• A Comparative Study of Rule-Based and Data-Driven Approaches in Industrial Monitoring [2.320417845168326]
  Rule-based systems offer high interpretability, deterministic behavior, and ease of implementation in stable environments.<n>Data-driven systems excel in detecting hidden anomalies, enabling predictive maintenance and dynamic adaptation to new conditions.<n>The paper suggests hybrid solutions, combining the transparency of rule-based logic with the analytical power of machine learning.
  arXiv  Detail & Related papers  (2025-09-19T10:31:59Z)
• Safely Learning Controlled Stochastic Dynamics [61.82896036131116]
  We introduce a method that ensures safe exploration and efficient estimation of system dynamics.<n>After training, the learned model enables predictions of the system's dynamics and permits safety verification of any given control.<n>We provide theoretical guarantees for safety and derive adaptive learning rates that improve with increasing Sobolev regularity of the true dynamics.
  arXiv  Detail & Related papers  (2025-06-03T11:17:07Z)
• Space-scale Exploration of the Poor Reliability of Deep Learning Models: the Case of the Remote Sensing of Rooftop Photovoltaic Systems [0.7499722271664147]
  Remote sensing of rooftop PV systems using deep learning emerged as a promising solution. Existing techniques are not reliable enough to construct up-to-date statistics on the rooftop PV fleet. This work proposes a comprehensive evaluation of the effects of distribution shifts on the classification accuracy of deep learning models trained to detect rooftop PV panels on overhead imagery.
  arXiv  Detail & Related papers  (2024-07-31T14:34:18Z)
• Enhancing Security in Federated Learning through Adaptive Consensus-Based Model Update Validation [2.28438857884398]
  This paper introduces an advanced approach for fortifying Federated Learning (FL) systems against label-flipping attacks. We propose a consensus-based verification process integrated with an adaptive thresholding mechanism. Our results indicate a significant mitigation of label-flipping attacks, bolstering the FL system's resilience.
  arXiv  Detail & Related papers  (2024-03-05T20:54:56Z)
• Conformal Policy Learning for Sensorimotor Control Under Distribution Shifts [61.929388479847525]
  This paper focuses on the problem of detecting and reacting to changes in the distribution of a sensorimotor controller's observables. The key idea is the design of switching policies that can take conformal quantiles as input. We show how to design such policies by using conformal quantiles to switch between base policies with different characteristics.
  arXiv  Detail & Related papers  (2023-11-02T17:59:30Z)
• Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions [60.26921219698514]
  We introduce a model-uncertainty-aware reformulation of CBF-based safety-critical controllers. We then present the pointwise feasibility conditions of the resulting safety controller. We use these conditions to devise an event-triggered online data collection strategy.
  arXiv  Detail & Related papers  (2022-08-23T05:02:09Z)
• An Energy and Carbon Footprint Analysis of Distributed and Federated Learning [42.37180749113699]
  Classical and centralized Artificial Intelligence (AI) methods require moving data from producers (sensors, machines) to energy hungry data centers. Emerging alternatives to mitigate such high energy costs propose to efficiently distribute, or federate, the learning tasks across devices. This paper proposes a novel framework for the analysis of energy and carbon footprints in distributed and federated learning.
  arXiv  Detail & Related papers  (2022-06-21T13:28:49Z)
• Forced Variational Integrator Networks for Prediction and Control of Mechanical Systems [7.538482310185133]
  We show that forced variational integrator networks (FVIN) architecture allows us to accurately account for energy dissipation and external forcing. This can result in highly-data efficient model-based control and can predict on real non-conservative systems.
  arXiv  Detail & Related papers  (2021-06-05T21:39:09Z)
• Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimization [57.88118988775461]
  We propose PROjected Feasibility (PROF) to enforce convex operational constraints within neural policies. We demonstrate PROF on two applications: energy-efficient building operation and inverter control.
  arXiv  Detail & Related papers  (2021-05-19T01:58:10Z)
• Cautious Reinforcement Learning with Logical Constraints [78.96597639789279]
  An adaptive safe padding forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process. Theoretical guarantees are available on the optimality of the synthesised policies and on the convergence of the learning algorithm.
  arXiv  Detail & Related papers  (2020-02-26T00:01:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.