Product assembly is often the last step in the manufacturing process. This task is usually performed by an assembly worker who needs to have practical experience and expertise. For complex products, the assembly may require a long time to study assembly plans. This paper presents a custom-designed Pick-to-Light system using Poka Yoke principles to make this activity easier. The created modular system with two-stage verification serves to guide the assembler precisely. It shows him on the display which parts he should use in a strictly defined assembly step. Our proposal aims to shorten assembly time and reduce the number of errors, which was supported by a case study in a small company with 30 employees. After analysing the data, we can declare that the proposed system significantly reduces the time required for assembly from 7 to 35% and reduces the error rate by 35%. The solution is scalable and flexible, as it can be easily adapted to display assembly steps for a different product.

One of the basic points of Industry 5.0 is to make the industry sustainable. There is a need to develop circular processes that reuse, repurpose, and recycle natural resources, and thus, reduce waste. This part can also include composite materials, which were used for some time in many areas. An essential feature of their applicability is the properties of these materials. The ratio of the individual components determines the properties of composite materials, and artificial intelligence machine learning (ML) techniques are already used to determine the optimal ratio. ML can be briefly described as computer science that uses existing data to predict future data. This approach is made possible by the current possibilities of collecting and analysing a large amount of data. It improves the chance of finding more variable influences (predictors) in the processes. These factors can be quantified more objectively; their mutual interactions can be identified, and, thanks to longer-term sampling, their future development behavior can be predictively modelled. The present article deals with the possibility of applying machine learning in predicting the absorption properties of composite material, which consists of a thermoplastic and matrix recycled polyvinyl butyral (PVB), obtained after recycling car glass windshields.

The thermal decomposition of wood chips from an apple tree is studied in a static air atmosphere under isothermal conditions. Based on the thermogravimetric analysis, the values of the apparent activation energy and pre-exponential factor are 34 ± 3 kJ mol⁻¹ and 391 ± 2 min⁻¹, respectively. These results have also shown that this process can be described by the rate of the first-order chemical reaction. This reaction model is valid only for a temperature range of 250–290 °C, mainly due to the lignin decomposition. The obtained results are used for kinetic prediction, which is compared with the measurement. The results show that the reaction is slower at higher values of degree of conversion, which is caused by the influence of the experimental condition. Nevertheless, the obtained kinetic parameters could be used for the optimization of the combustion process of wood chips in small-scale biomass boilers.

Quality of production is very important part of successful company. Through the variability of production can be generated the products, which not achieve requirements of quality. For company it means loss. Prediction of evaluation of the achievement level of quality of production process is possible way how can be eliminated losses of the company.In the presented contribution is shown the possibility of using tools of software product Matlab to create a predictive model for evaluating the quality of the production process. There are described the tools that enable the creation an appropriate model. In this model were used the basic tools of statistical process control and their graphic representation in the form of diagram.

The increasing complexity of artificial intelligence and machine learning models has raised concerns about balancing model accuracy and interpretability. While advanced software tools facilitate model design, they also introduce challenges in selecting models that offer both high quality and manageable complexity. Validation techniques such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the Akaike Information Criterion (AIC) enable quantitative assessment, but empirical studies indicate that higher complexity does not always improve predictive performance. This study proposes an approach to evaluate model complexity versus accuracy in predicting the absorption properties of composite materials with varying textile fibre content (10%, 20%, 30%, 40%). Using MATLAB’s Curve Fitting Toolbox, we assessed polynomial, Fourier, and Gaussian regression models. The Gaussian regression model with six parameters (Gauss6) achieved the best balance between complexity and accuracy (R² = 0.9429; RMSE = 0.013537; MAE = 0.004885). Increasing parameters beyond six showed diminishing returns, as confirmed by AIC (−2806.93 for Gauss6 vs. −2847.17 for Gauss7). These findings emphasise that higher model complexity does not necessarily enhance quality, highlighting the importance of structured model validation. This study provides insights for optimising predictive modelling in material science and other domains.

The paper presents the proposal for the expressed some properties of the pneumatic artificial muscle. The solution of the differential equation is expressed by the application of the polar coordinate. This equation is the model for the movement of the pneumatic artificial muscle.