Soft sensors are increasingly being used to provide important information about production processes that is otherwise only available through off-line laboratory analysis. However, usually, they are developed for a specific application, for which thorough process analysis is performed to provide information for the appropriate selection of model type and model structure. Wide industrial application of soft sensors, however, requires a method for soft sensor development that has a high level of automatism and is applicable to a significant number of industrial processes. A class of processes that is very common in the industry are processes with distinct operating conditions. In this paper, an algorithm that is suitable for the development of soft sensors for this class of processes is presented. The algorithm possesses a high level of automatism, as it requires minimal user engagement regarding the structure of the model, which makes it suitable for implementation as a customary industrial solution. The algorithm is based on a radial basis function artificial neural network, and it enables the automatic selection of the model structure and the determination of model parameters, only based on the training data set. The testing of the presented algorithm is done on the cement production process, since it represents a process with distinct operating conditions. The results of the test show that, besides providing a high level of automatism in model development, the presented algorithm generates a soft sensor with high estimation performance.

In recent years, bacteria-based self-healing has emerged as a promising bioengineering strategy to address the self-repair of cracks in cement-based materials, which represent one of the persistent durability challenges. This approach relies on microbiologically induced calcium carbonate (CaCO₃) precipitation (MICP), in which metabolically active bacteria promote CaCO₃ formation of crystals that can heal cracks and restore material integrity. This study compares the self-healing potential of a natural (N-) alkaline soil Bacillus licheniformis strain with a UV-strain (phenotypic mutant) generated through controlled UV exposure followed by adaptive evolution. Both strains were evaluated under conditions relevant to cementitious environments. The UV-strain exhibited enhanced ureolytic performance, reaching urease activity of 0.32 U/mg compared to 0.24 U/mg in the N-strain. This translated into improved biomineralization, with CaCO₃ precipitation reaching 2.37 mg versus 2.23 mg/100 mL in the N-strain. Additionally, the UV-strain showed increased cell hydrophobicity and aggregation, indicating improved nucleation potential and surface-mediated mineral deposition. Multivariate analysis confirmed strong correlations between ureolytic metabolism, alkalization, and mineral formation, while artificial neural network (ANN) modeling (MLP 6-10-14) successfully predicted biomineralization-related parameters with high accuracy (R² > 0.90 for urease activity, NH₄⁺, ΔpH, and CaCO₃). The results demonstrate that UV-induced phenotypic adaptation can enhance biomineralization efficiency with minor trade-offs in physiological robustness. For the first time, that controlled UV-induced phenotypic adaptation can be used as a targeted strategy to enhance biomineralization efficiency in B. licheniformis, while maintaining functional stability under cement-relevant conditions. These findings provide a novel framework for tailoring bacterial performance in self-healing systems for construction biotechnology.

Understanding the temperature–working condition relationship is crucial for optimizing machining processes to ensure dimensional accuracy, surface finish quality, and overall spindle longevity. Monitoring and controlling spindle temperature through appropriate cooling systems and operational parameters are essential for efficient and reliable machining operations. This paper presents an in-depth analysis of the thermal equilibrium and deformation characteristics of a high-speed motorized spindle unit utilized in grinding machine tools. Through a series of thermal equilibrium experiments and meticulous data acquisition, the study investigates the nuanced influence of various working conditions, including spindle speeds, coolant types, and coolant flow rates, on spindle temperatures and thermal deformations. Leveraging the power of Artificial Neural Networks (ANNs), predictive models are meticulously developed to accurately forecast spindle behavior. Subsequently, the models are seamlessly transitioned to a cloud computing infrastructure to ensure remote accessibility and scalability, facilitating real-time monitoring and forecasting of spindle performance. The validity and reliability of the predictive models are rigorously assessed through comparison with experimental data, demonstrating excellent agreement and high accuracy in forecasting spindle thermal behavior. Furthermore, the study underscores the critical role of key working condition variables as precise predictors of spindle temperature and thermal deformation, emphasizing their significance in optimizing overall spindle efficiency and performance. This comprehensive analysis offers valuable insights and practical implications for enhancing spindle operation and advancing the field of grinding machine tools.

This study evaluated the performance of four groups of digital filtering pipelines - simple and complex combinations of rectification, low-pass, and notch filters, for realtime EMG envelope extraction, a common approach in myoelectric control systems. Evaluation metrics used were Root Mean Square Error (RMSE), Coefficient of determination ($\mathbf{R}^{\mathbf{2}}$), Kolmogorov-Smirnov (KS) test, and execution time, with the latter analyzed using box plots to assess. The results showed that the first and the third groups of filters had the most variable runtime, while the second and the fourth were more consistent. The fourth group of filters showed the lowest RMSE and KS test values, the highest $\mathbf{R}^{\mathbf{2}}$, indicating the best predictive performance, and thus being most adequate for real-time applications due to the balance between its simplicity and the quality of the obtained envelope. The findings emphasize the importance of including execution-time analysis when selecting digital filters.