Estimation of Tool Life in the Milling Process-Testing Regression Models.

The article presents an attempt to identify an appropriate regression model for the estimation of cutting tool lifespan in the milling process based on the analysis of the R2 parameters of these models. The work is based on our own experiments and the accumulated database (which we make available for further use). The study uses a Haas VF-1 milling machine equipped with vibration sensors and based on a Beckhoff PLC data collector. As the acquired sensor data are continuous, and in order to account for dependencies between them, regression models were used. Support Vector Regression (SVR), decision trees and neural networks were tested during the work. The results obtained show that the best prediction results with the lowest error values were obtained for two-dimensional neural networks using the LBFGS solver (93.9%). Very similar results were also obtained for SVR (93.4%). The research carried out is related to the realisation of intelligent manufacturing dedicated to Industry 4.0 in the field of monitoring production processes, planning service downtime and reducing the level of losses resulting from damage to materials, semi-finished products and tools.

Quantitative and Qualitative Analysis of Agricultural Fields Based on Aerial Multispectral Images Using Neural Networks.

This article presents an integrated system that uses the capabilities of unmanned aerial vehicles (UAVs) to perform a comprehensive crop analysis, combining qualitative and quantitative evaluations for efficient agricultural management. A convolutional neural network-based model, Detectron2, serves as the foundation for detecting and segmenting objects of interest in acquired aerial images. This model was trained on a dataset prepared using the COCO format, which features a variety of annotated objects. The system architecture comprises a frontend and a backend component. The frontend facilitates user interaction and annotation of objects on multispectral images. The backend involves image loading, project management, polygon handling, and multispectral image processing. For qualitative analysis, users can delineate regions of interest using polygons, which are then subjected to analysis using the Normalized Difference Vegetation Index (NDVI) or Optimized Soil Adjusted Vegetation Index (OSAVI). For quantitative analysis, the system deploys a pre-trained model capable of object detection, allowing for the counting and localization of specific objects, with a focus on young lettuce crops. The prediction quality of the model has been calculated using the AP (Average Precision) metric. The trained neural network exhibited robust performance in detecting objects, even within small images.

Frugal Heart Rate Correction Method for Scalable Health and Safety Monitoring in Construction Sites.

Continuous, real-time monitoring of occupational health and safety in high-risk workplaces such as construction sites can substantially improve the safety of workers. However, introducing such systems in practice is associated with a number of challenges, such as scaling up the solution while keeping its cost low. In this context, this work investigates the use of an off-the-shelf, low-cost smartwatch to detect health issues based on heart rate monitoring in a privacy-preserving manner. To improve the smartwatch's low measurement quality, a novel, frugal machine learning method is proposed that corrects measurement errors, along with a new dataset for this task. This method's integration with the smartwatch and the remaining parts of the health and safety monitoring system (built on the ASSIST-IoT reference architecture) are presented. This method was evaluated in a laboratory environment in terms of its accuracy, computational requirements, and frugality. With an experimentally established mean absolute error of 8.19 BPM, only 880 bytes of required memory, and a negligible impact on the performance of the device, this method meets all relevant requirements and is expected to be field-tested in the coming months. To support reproducibility and to encourage alternative approaches, the dataset, the trained model, and its implementation on the smartwatch were published under free licenses.

Manufacturing Polymer Model of Anatomical Structures with Increased Accuracy Using CAx and AM Systems for Planning Orthopedic Procedures.

Currently, medicine uses typical industrial structure techniques, including reverse engineering, data processing, 3D-CAD modeling, 3D printing, and coordinate measurement techniques. Taking this into account, one can notice the applications of procedures used in the aviation or automotive industries based on the structure of Industry 4.0 in the planning of operations and the production of medical models with high geometric accuracy. The procedure presented in the publication shortens the processing time of tomographic data and increases the reconstruction accuracy within the hip and knee joints. The procedure allows for the partial removal of metallic artifacts from the diagnostic image. Additionally, numerical models of anatomical structures, implants, and bone cement were developed in more detail by averaging the values of local segmentation thresholds. Before the model manufacturing process, additional tests of the PLA material were conducted in terms of its strength and thermal properties. Their goal was to select the appropriate type of PLA material for manufacturing models of anatomical structures. The numerical models were divided into parts before being manufactured using the Fused Filament Fabrication technique. The use of the modifier made it possible to change the density, type of filling, number of counters, and the type of supporting structure. These treatments allowed us to reduce costs and production time and increase the accuracy of the printout. The accuracy of the manufactured model geometry was verified using the MCA-II measuring arm with the MMDx100 laser head and surface roughness using a 3D Talyscan 150 profilometer. Using the procedure, a decrease in geometric deviations and amplitude parameters of the surface roughness were noticed. The models based on the presented approach allowed for detailed and meticulous treatment planning.

Modeling and Analysis of Anomalies in the Network Infrastructure Based on the Potts Model.

The paper discusses issues concerning the occurrence of anomalies affecting the process of phase transitions. The considered issue was examined from the perspective of phase transitions in network structures, particularly in IT networks, Internet of Things and Internet of Everything. The basis for the research was the Potts model in the context of IT networks. The author proposed the classification of anomalies in relation to the states of particular nodes in the network structure. Considered anomalies included homogeneous, heterogeneous, individual and cyclic disorders. The results of tests and simulations clearly showed the impact of anomalies on the phase transitions in the network structures. The obtained results can be applied in modelling the processes occurring in network structures, particularly in IT networks.

Methodology for the Quality Control Process of Additive Manufacturing Products Made of Polymer Materials.

The objective of this publication is to present a quality control methodology for additive manufacturing products made of polymer materials, where the methodology varies depending on the intended use. The models presented in this paper are divided into those that are manufactured for the purpose of visual presentation and those that directly serve the needs of the manufacturing process. The authors also a propose a comprehensive control system for the additive manufacturing process to meet the needs of Industry 4.0. Depending on the intended use of the models, the quality control process is divided into three stages: data control, manufacturing control, and post-processing control. Research models were made from the following materials: RGD 720 photopolymer resin (PolyJet method), ABS M30 thermoplastic (FDM method), E-Partial photopolymer resin (DLP method), PLA thermoplastic (FFF method), and ABS thermoplastic (MEM method). The applied measuring tools had an accuracy of at least an order of magnitude higher than that of the manufacturing technologies used. The results show that the PolyJet method is the most accurate, and the MEM method is the least accurate. The findings also confirm that the selection of materials, 3D printing methods, and measurement methods should always account not only for the specificity and purpose of the model but also for economic aspects, as not all products require high accuracy and durability.

An Analysis of the Casting Polymer Mold Wear Manufactured Using PolyJet Method Based on the Measurement of the Surface Topography.

An important factor having an impact on the condition of machine parts is their surface topography. For instance, in the production of a molded element in casting or injection molding processes, the surface topography of the molding cavity has a significant impact on the surface condition of the product. An analysis of the wear of a mold made with the PolyJet technique was performed in this work, and we examined the surface topography using the stylus method after casting a wax model of the turbine blade. The surface topographies showed a gradual degradation of the mold cavity surface. After the manufacture of 40 castings, there was a significant deformation of the microstructure of the mold cavity. The maximum height value (Sz) parameter had the most dynamic change from 18.980 to 27.920 µm. Its growth dynamics are mainly influenced by maximum peak height (Sp) rather than the maximum pit height (Sv) parameter. In the case of the root mean square height (Sq) and arithmetic mean height (Sa), their gradual increases can be seen from 2.578 to 3.599 µm and from 2.038 to 2.746 µm. In the case of the value of the skewness (Ssk) parameter, a small positive skew was observed. As for the kurtosis (Sku) values, the distributions are clearly leptokurtic.

Responsiveness of the Sensor Network to Alarm Events Based on the Potts Model.

The paper aims to present modelling the sensor network operation based on the Potts model. The authors presented own approach based on three states in which each node can be. The change in the state of a given node depends on its current state, the impact of surrounding nodes on it, but also values of the parameters measured. Therefore, the Hamiltonian was introduced as a dependence of both exceeding the limit value of a measured parameter (corresponding to an alarm event), and the state of the battery powering a given node of a sensor. The simulations of the implemented algorithm based on the adopted model presented in the paper relate to the measurement of temperature by a network of sensors. However, this model is universal and can be applied to examine the behaviour of the sensor infrastructure performing various measurements. Moreover, it may simulate the functioning of the critical network infrastructure or sensor networks and industrial sensors supporting the functioning of Industry 4.0.