https://www.mdu.se/

Machine learning is an increasingly popular method for modeling complex systems. A common machine learning model is the neural network, which can be trained to represent complicated functions to a high accuracy. However, neural networks often grow large and complex. Recent work is looking at how to abstract networks to yield simpler representations while retaining some property of the original network — for instance, such that for every input the abstracted network's output is at least as large as the original. In this work, we build on previous ideas and extend them to also consider the input layer. Sometimes the input vector has a large size while only a few of the elements are significant in the computation of the output. We propose to use a trained neural network model to identify insignificant input elements, i.e., elements which do not contain important information. We show how the presented abstraction method for the input layer can be utilized to achieve this.

Modern power systems are often equipped with advanced monitoring infrastructure that can collect vast and diverse data streams. Data-driven approaches, such as anomaly detection (AD), can be applied to these data, complementing existing monitoring practices, and supporting adaptive and intelligent decision-making. Industrial anomaly detection is challenging due to the predominance of normal operational data, rare anomalous events, and limited labeled samples. The success of unsupervised AD approaches are often dependent on the proper thresholds, which determine whether or not a sample is anomalous. The often manual process of setting the thresholds can be challenging in ensuring the accuracy, reliability, and robustness of AD in a wide range of operational scenarios. In this paper, a self-supervised, meta-learning-based anomaly detection framework is proposed. The method combines multiple models to exploit complementary strengths and uses reconstruction errors of an ensemble of autoencoders as meta-features to improve detection of subtle anomalies. By generating labels from meta-features, the approach supports learning in label-scarce scenarios. Experiments on different public and industrial datasets show that integrating meta-features and generated pseudo-labels achieves performance comparable to supervised learning based on the ground truth labels, demonstrating the proposed approach as a promising solution for real-world, label-scarce industrial applications.

The validation of Automated Driving Systems (ADSs) has shifted from distance-based metrics to Scenario-Based Testing (SBT). Large Language Models (LLMs) have emerged as powerful tools with potential for generating vehicular scenarios at scale. However, generative models used for direct simulation synthesis produce inadequate output, therefore necessitating a more structured compilation approach. We present HASCO (Hybrid AI Simulation COmpiler), a system that translates natural-language driving scene specifications into executable simulation artifacts (XOSC/XODR files) for the esmini/OpenSCENARIO ecosystem. While LLMs excel at narrative parsing, we demonstrate that direct synthesis of simulation artifacts fails in the vast majority of cases due to hallucinated physics or schema violations. To resolve this, HASCO treats scenario creation as a compilation task rather than a generative one. The pipeline supports three compilation paths: direct synthesis, a Python intermediate (via scenariogeneration), and an ontology-guided path that grounds intent into an intermediate representation before compilation. We further evaluate a self-judging mechanism for automated repair. Across six operating modes evaluated on 40 real-world accident reports, the ontology-guided and Python-based compilers achieve 95% and 90% executability rates, respectively, compared to 5% for direct synthesis. We additionally evaluate outputs on semantic fidelity, positioning HASCO as a robust tool for forensic scene reconstruction.

To address safety concerns in industrial systems, we propose a framework for forecasting CPU load with respect to a predetermined threshold, allowing customers to add tasks from a predefined library. Existing tools, akin to Windows Task Manager, provide limited insights due to their aggregate nature and high computational overhead. Our approach uses conformal prediction for rapid uncertainty-aware forecasts and Shapley value analysis to quantify individual task contributions to the CPU load. This proof-of-concept framework improves system safety assessment by addressing key research questions in load prediction and validation, paving the way for refined measurement methodologies in industrial applications.

Given increased complex data with high dimensions, feature selection aims to select a subset of features to increase the efficiency of machine learning. This paper proposes a new feature selection method based on membrane computing. The proposed method has two main advantages. First, it provides a new solution to search for feature combinations while requiring no model construction (which is time-consuming) to evaluate a feature subset. Second, feature selection is embedded in a membrane clustering algorithm, which is designed to enable searching for the best feature subset and finding active cluster centres at the same time. The designed clustering algorithm mimics the behavior of multiple cells and it has stronger global search ability than existing evolutionary algorithms. The efficacy of the proposed method has been shown by the evaluation of a set of benchmark data sets.

Integrating machine learning into computer architecture simulation offers a new approach to performance analysis, moving away from traditional algorithmic methods. While existing simulators accurately replicate hardware, they often suffer from slow execution, complex documentation, and require deep CPU knowledge, limiting their usability for quick insights. This paper presents a deep learning-based approach for simulating a key CPU component, cache memory. Our model "learns" cache characteristics by observing cache miss distributions, without needing detailed manual modeling. This method accelerates simulations and adapts to different program needs, demonstrating accuracy comparable to traditional simulators. Tested on Sysbench and image processing algorithms, it shows promise for faster, scalable, and hardware-independent simulations.

Digital Twins (DTs) are virtual representations of physical products in many dimensions, such as geometry and behaviour. As a backbone of Industry 4.0, DTs help interpret and even predict the behaviour of physical processes, provide a virtual testbed for maintenance and upgrade, and enable automatic decision-making supported by artificial intelligence. Despite the promising future, challenges exist, such as the absence of a framework that facilitates the development and application of DTs in industrial contexts. We propose a service-oriented architecture (SOA) DT framework for dynamic and robust distributed systems. The framework contains two types of services. One includes the services provided to the users and is supported by an orchestration mechanism to ensure a quality of service (QoS). The other one refers to the common functions of all DTs. Further, we describe the DT-based decision-making enabled by our QoS-oriented learning of the framework and a Hoare-logic-based verification of QoS. 

Anomaly detection in industrial systems is crucial for preventing equipment failures, ensuring risk identification, and maintaining overall system efficiency. Traditional monitoring methods often rely on fixed thresholds and empirical rules, which may not be sensitive enough to detect subtle changes in system health and predict impending failures. To address this limitation, this paper proposes, a novel self-supervised learning technique using autoencoder based hybrid models called Attention-based convolutional autoencoder (ABCD) for risk detection and mapping risk value derive to the maintenance planning. ABCD learns the normal behavior of conductivity from historical data of a real-world industrial cooling system and reconstructs the input data, identifying anomalies that deviate from the expected patterns. The framework also employs calibration techniques to ensure the reliability of its predictions. Evaluation of results demonstrate that with the attention mechanism in ABCD a 57.4% increase in performance and a reduction of false alarms by 9.37% is seen compared to without attentions. This approach can effectively detect risks, the risk priority rank mapped to maintenance, providing valuable insights for cooling system designers and service personnel. Calibration error of 0.03% indicates that the model is well-calibrated and enhances model's trustworthiness, enabling informed decisions about maintenance strategies.

Digital Twins (DTs) serve as the backbone of Industry 4.0, offering virtual representations of actual systems, enabling accurate simulations, analysis, and control. These representations help in predicting system behaviour, facilitating multiple real-time tests, and reducing risks and costs while identifying optimization areas. DTs meld cyber and physical realms, accelerating the design and modelling of sustainable innovations. Despite their potential, the complexity of DTs presents challenges in their industrial application. We sketch here an approach to build an adaptable and trustable framework for building and operating DT systems, which is the basis for the academia-industry project A Digital Twin Framework for Dynamic and Robust Distributed Systems (D-RODS). D-RODS aims to address the challenges above, aiming to advance industrial digitalization and targeting areas like system efficiency, incorporating AI and verification techniques with formal support. 

In the power domain, effective maintenance decision-making is crucial for asset reliability, availability, and maintainability (RAM). This paper proposes a framework that integrates existing practices with data-driven methods, considering factors like maintenance maturity and business case justification. It navigates two strategies: business pull, that aligns with market needs, and technology push, that focuses on data-driven predictive methods to optimize maintenance planning by early failure detection. Combining business pull and technology push aligns solutions with market needs while leveraging innovations to create new opportunities. This integration helps organizations optimize operations, enhance decision-making, and stay competitive while meeting RAM metrics. An example application is detailed in separate work.