In this work, we present and test an approach based on an inverse model applicable to the control of induction heat treatments. The inverse model is comprised of a simplified analytical forward model trained with experiments to predict and control the temperature of a location in a cylindrical sample starting from any initial temperature. We solve the coupled nonlinear electromagnetic-thermal problem, which contains a temperature dependent parameter $\alpha$ to correct the electromagnetic field on the surface of a cylinder, and as a result effectively the modeled temperature elsewhere in the sample. A calibrated model to the measurement data applied with the process information such as the operating power level, current, frequency, and temperature provides the basic ingredients to construct an inverse model toolbox, which finally enables us to conduct experiments with more specific goals. The input set values of the power supply, i.e., the power levels in the test rig control system, are determined within an iterative framework to reach specific target temperatures in prescribed times. We verify the concept on an induction heating test rig and provide two examples to illustrate the approach. The advantages of the method lie in its simplicity, computationally cost effectiveness and independence of a prior knowledge of the internal structure of power supplies.

Remaining useful life (RUL) prediction is central to prognostics and reliability assessment of light-emitting diode (LED) systems. Their unknown long-term service life remaining when subject to specific operating conditions is affected by various sources of uncertainty stemming from production of individual system components, application of the whole system, measurement and operation. To enhance the reliability of model-based predictions, it is essential to account for all of these uncertainties in a systematic manner. This paper proposes a Bayesian hierarchical modelling framework for inverse uncertainty quantification (UQ) in LED operation under thermal loading. The main focus is on the LED systems’ operational thermal resistances, which are subject to system and application variability. Posterior inference is based on a Markov chain Monte Carlo (MCMC) sampling scheme using the Metropolis–Hastings (MH) algorithm. Performance of the method is investigated for simulated data, which allow to focus on different UQ aspects in applications. Findings from an application scenario in which the impact of disregarded uncertainty on RUL prediction is discussed highlight the need for a comprehensive UQ to allow for reliable predictions.

In this work we apply data-driven models for predicting tensile strength of steel coils from chemical composition and process parameters. The data originates from steel production and includes a full chemical analysis, as well as many process parameters and the resulting strength properties from tensile tests. We establish a data pre-processing pipeline, where we apply data cleaning and feature engineering to create a machine-readable dataset suitable for various modeling tasks. We compare prediction quality, complexity and interpretability of pure machine learning (ML) models, either with the full feature set or a reduced one. Dimensionality reduction methods are used to reduce the number of features and therefore reduce complexity, either with a smart selection method or feature encoding, where features are combined and the included information is preserved. In order to determine key features of our models, we are investigating feature importance ratings, which can be used as a feature selection criteria. Furthermore, we are highlighting methods to explain predictions and determine the impact of every feature in every observation applicable for any ML model.