Search

Conveyor belts are vital for material transportation in coal mines due to their cost-effectiveness and versatility. These belts endure significant wear from harsh operating conditions, risking substantial financial losses if they fail. This study develops five artificial neural network (ANN) models to predict conveyor belt damage using 11 parameters from the Belchatow brown coal mine in Poland. The models target five outputs: number of repairs and cable cuts, cumulative number of repairs and cable cuts, and their ages. Various optimizers (Adam, Nadam, RMSprop, Adamax, and stochastic gradient descent or SGD) and activation functions (ReLU, Swish, sigmoid, tanh, Leaky ReLU, and softmax) were tested to find the optimal configurations. The predictive performance was evaluated using three error indicators against actual mine data. Superior models can forecast belt behavior under specific conditions, aiding proactive maintenance. The study also advocates for the Diagbelt+ system over human inspections for failure detection. This modeling approach enhances proactive maintenance, preventing total system breakdowns due to belt wear.

Improving production processes includes not only activities concerning manufacturing itself, but also all the activities that are necessary to achieve the main objectives. One such activity is transport, which, although a source of waste in terms of adding value to the product, is essential to the realization of the production process. Over the years, many methods have been developed to help manage supply and transport in such a way as to reduce it to the necessary minimum. In the paper, the problem of delivering components to a production area using trains and appropriately laid-out carriages was described. It is a milk run stop locations problem (MRSLP), whose proposed solution is based on the use of heuristic algorithms. Intelligent solutions are getting more and more popular in the industry because of the possible advantages they offer, especially those that include the possibility of finding an optimum local solution in a relatively short time and the prevention of human errors. In this paper, the applicability of three algorithms – tabu search, genetic algorithm, and simulated annealing – was explored.

The paper deals with the issue of production scheduling for various types of employees in a large manufacturing company where the decision-making process was based on a human factor and the foreman’s know-how, which was error-prone. Modern production processes are getting more and more complex. A company that wants to be competitive on the market must consider many factors. Relying only on human factors is not efficient at all. The presented work has the objective of developing a new employee scheduling system that might be considered a particular case of the job shop problem from the set of the employee scheduling problems. The Neuro-Tabu Search algorithm and the data gathered by manufacturing sensors and process controls are used to remotely inspect machine condition and sustainability as well as for preventive maintenance. They were used to build production schedules. The construction of the Neuro-Tabu Search algorithm combines the Tabu Search algorithm, one of the most effective methods of constructing heuristic algorithms for scheduling problems, and a self-organizing neural network that further improves the prohibition mechanism of the Tabu Search algorithm. Additionally, in the paper, sustainability with the use of Industry 4.0 is considered. That would make it possible to minimize the costs of employees’ work and the cost of the overall production process. Solving the optimization problem offered by Neuro-Tabu Search algorithm and real-time data shows a new way of production management.

This paper deals with an assessment of the effectiveness of resource management in production processes. A comprehensive and standardized approach to the issue of effectiveness contributes to the maximization of the potential of production resources. In this paper, the concept of effectiveness was used in the sense of the praxeological approach, and its components were distinguished by availability, performance and quality, which were assessed through the prism of losses occurring in production processes. The main purpose of this work was to develop a method for assessing the effectiveness of the use of available resources when implementing production processes. The method is based on a set of quantitative indicators and takes into account the categorization of production losses. Losses in availability, performance and quality in terms of areas of production, logistics, and maintenance, as well as organization and management, were identified. It was developed in response to the research gap identified in the literature review, which showed that there is a lack of a quantitative method for assessing the effectiveness of production processes. The method also takes into account the categorization of production losses, and at the same time allows the contribution of the main areas (production and production-related) with regard to the generation of these losses. The method is primarily intended to identify the causes of problems occurring in any production process, to determine their importance in a measurable way, and to monitor the course of processes after introducing changes of a different nature. The method was verified on a real example in a branch of an automotive industry company located in Lower Silesia.

Standardization is a key element in the effective use of lean manufacturing methodologies and tools for achieving process sustainability. Their combination is conducive to eliminating waste and improving the efficiency of production processes and guarantees the company that employees use the most efficient tools and do not waste time on unnecessary activities. These activities can be further improved by using digital solutions, in accordance with the concept of Industry 4.0. Therefore, the authors have developed the e-Lean system, whose task is to digitize selected lean manufacturing tools. The subject of this work is analysis of the functionality and effectiveness of the essential part of the e-Lean system in the form of specialized TPM (Total Productive Maintenance) software as an application. During implementation in a construction production company, the TPM application was tested by lean manufacturing and maintenance specialists. The research consisted of assessing the functionality and efficiency of processes in relation to conventional TPM solutions. Additional functionalities of the e-Lean system have been confirmed, such as systemic approval of machinery inspection, which requires passing all necessary steps at individual inspection points, direct access for supervisors to the results of inspection activities and their status, direct and easy access to photographic documentation of machines added during inspection both in optimization of working time and its course (e.g., the optimal number of steps taken by the employee during the inspection), as well as an efficient system of motivating employees (collecting points). The improvement in the effectiveness of processes was determined by measuring the control times for three control points (polymerization furnace, packing area, and defibering machines). The average control time was reduced from 16,200 to 13,923 s. Thus, thanks to the use of the application, it was found that the efficiency of using the TPM tool was increased by approx. 15% compared to previously used non-digital solutions.

Despite scientific and clinical advances, stroke is still considered one of the main causes of disability, including gait disorders. The search for more effective methods of gait re-education in post-stroke patients is one of the most important issues in contemporary neurorehabilitation. In this paper, we propose a transformation of the feature space and definition of class labels in the post-stroke gait problem to more efficiently study related phenomena and assess gait faster. Clustering is used to define two class labels (improvement and recurrence) in the data labeling process. The proposed approach was tested on a real-world dataset consisting of 50 patients (male and female, aged 49–82 years) after ischemic stroke who participated in a gait rehabilitation program. Gait in the study was described using speed, cadence, and stride length and their normalized values. Ten treatment sessions (10 therapy days) were conducted over two weeks (10 working days). The same specialist took measurements, and hence inter-rater reliability can be neglected. Machine learning methods, support vector machine and quadratic discriminant analysis were used to classify post-stroke gait for three cases with different class labels. The proposed novel approach, characterized by its speed of execution and accuracy of classification, may be helpful for screening, better targeting, and rehabilitation monitoring. The proposed approach minimizes clinical testing and supports the work of physicians, physiotherapists, and diagnosticians.

The binary classifiers are appropriate for classification problems with two class labels. For multi-class problems, decomposition techniques, like one-vs-one strategy, are used because they allow the use of binary classifiers. The ensemble selection, on the other hand, is one of the most studied topics in multiple classifier systems because a selected subset of base classifiers may perform better than the whole set of base classifiers. Thus, we propose a novel concept of the dynamic ensemble selection based on values of the score function used in the one-vs-one decomposition scheme. The proposed algorithm has been verified on a real dataset regarding the classification of cutting tools. The proposed approach is compared with the static ensemble selection method based on the integration of base classifiers in geometric space, which also uses the one-vs-one decomposition scheme. In addition, other base classification algorithms are used to compare results in the conducted experiments. The obtained results demonstrate the effectiveness of our approach.

Aim: In this study, we aimed to assess the correlation between diabetes mellitus (DM) and the retinal vein occlusion (RVO) based on skin autofluorescence (SAF) measurement, which reflects the accumulation of advanced glycation end products (AGE) in patients who have undergone an episode of central retinal vein occlusion (CRVO) or branch retinal vein occlusion (BRVO). Material and methods: In total, 23 patients (16 males, 7 females) with RVO were included in this study. Among these 23 participants, 12 (52%) had been diagnosed with CRVO and 11 (48%) with BRVO. The control group consisted of 14 healthy volunteers (11 females, 3 males). To calculate the risk of cardiovascular diseases (CVD) and DM, we conducted SAF examinations. We compared the SAF levels in three groups of patients: (1) with CRVO, (2) with BRVO, and (3) the control group. Basic demographic and clinical information and detailed history of the concurrent diagnoses of systemic diseases, such as systemic hypertension (HTN), DM, hyperlipidemia (HL), and heart diseases, were obtained. Results: In total, 10 (43.5%) patients were diagnosed with DM, 6 (55%) in the BRVO group and 4 (33%) in the CRVO group. The mean SAF value was significantly higher in the BRVO group than in the control group (2.64 a.u. and 2.35 a.u., respectively) (p = 0.023). More patients with risk of DM were identified in the CRVO group than in the BRVO group (p = 0.024). Conclusions: The advanced glycation end products (AGE) in the skin autofluorescence (SAF) is a viable method of evaluating the risk of DM in patients with RVO. We confirmed a correlation between RVO and DM, which was significantly pronounced in the CRVO form, although further carefully devised studies on the relationship between RVO and DM with a larger number of responders should be conducted in the future.

Production and maintenance tasks apply for access to the same resources. Maintenance-related machine downtime reduces productivity, but the costs incurred due to unplanned machine failures often outweigh the costs associated with predictive maintenance. Costs incurred due to unplanned machine failure include corrective maintenance, reworks, delays in deliveries, breaks in the work of employees and machines. Therefore, scheduling of production and maintenance tasks should be considered jointly. The problem of generating a predictive schedule with given constrains is considered. The objective of the paper is to develop a scheduling method that reflects the operation of the production system and nature of disturbances. The original value of the paper is the development of the method of a basic schedule generation with the application of the Ant Colony Optimisation. A predictive schedule is built by planning the technical inspection of the machine at time of the predicted failure-free time. The numerical simulations are performed for job/flow shop systems.

We evaluated the effect of three monthly intravitreal injections of aflibercept on the serum concentration of interleukin 17A (IL-17A), monocyte chemoattractant protein 1 (MCP-1/CCL2), vascular endothelial growth factor (VEGF) and placental growth factor (PlGF) in treatment-naive patients with neovascular age-related macular degeneration (nAMD). Twenty-two eyes of twenty-two patients with nAMD scheduled for the initial loading phase of intravitreal aflibercept (2 mg/0.05 mL) were included. Serum VEGF, PlGF, MCP-1/CCL2 and IL-17A levels were determined four times in each individual—just before the first injection, 2–3 days after the first injection, just before the third injection, and then 2–3 days after the third aflibercept injection. A statistically significant difference was found between the serum PlGF and IL-17A levels measured before the first injection and after the initial loading phase, with a mean value (MV) of 440.884 vs. 302.151 (p = 0.023) for PlGF and MV = 139.088 pg/mL vs. 151.233 pg/mL (p = 0.016) for IL-17A, respectively. There were no statistically significant differences for VEGF and MCP-1/CCL2 between any of the compared measurements. We reveal that repeated injections of aflibercept promote an increase in serum IL-17A concentration, which may lead to a systemic inflammatory response mediated by IL-17A, but not by MCP-1.

Optical coherence tomography (OCT) is a high-speed and non-contact optical imaging technology widely used for noninvasive cross-sectional imaging of biological objects. Two main OCT technologies have been developed: time domain and Fourier domain technologies. The latter can be further divided into spectral domain OCT, which uses a broadband light source and a spectrometer as a detector, and swept source OCT, which employs a quickly-rotating laser source. Advances in OCT technology have made it one of the most helpful devices in ophthalmic practice. Fourier OCT has revolutionized imaging of the posterior segment of the eye, as well as of anterior structures and has enhanced the ability to diagnose and manage patients. It provides high-resolution information about the tear film, contact lens (CL), a qualitative and quantitative assessment of the anterior eye that is important in CL fitting, and allows possible eye surface changes while wearing CLs to be monitored. Potential swept source OCT technology applications include industrial processes of lens design and quality control. In this paper, we describe clinical applications ant outline a variety of multifunctional uses of OCT in the field of refractive error correction with CLs.