Robert Sałat

The objective of this paper is to propose a novel bidirectional modeling framework using simplified neuro-fuzzy networks to approximate the complex dependencies between the workability parameters of self-compacting concrete (SCC) and the quantities of its five principal ingredients, namely cement, fly ash, water, additives, and admixtures. The forward model predicts seven key workability parameters based on the input ingredients and is essential for assessing the quality and performance of fresh SCC before production begins. In contrast, the backward model is trained to recommend the specific quantities of input ingredients required to achieve the expected SCC parameters. A comprehensive dataset consisting of 480 field-tested SCC mixtures was developed and used to train simplified Takagi–Sugeno–Kang (sTSK) networks. The numerical experiments demonstrated high accuracy, with the forward model achieving average relative errors of less than 2.46% and the backward model achieving an average relative error of 1.62%. These findings highlight the effectiveness of the proposed solutions in developing highly accurate approximation models. This study introduces a robust backward estimation approach, addressing a gap left by conventional forward-only models. Moreover, by incorporating Mahalanobis distance into the sTSK architecture, the proposed models use three times fewer nonlinear parameters than classical versions. This reduction enables their potential practical application in real-field concrete mixing and production systems for on-site quality control in production environments.

The aim of this study was to explore the use of neural networks as a decision-support tool for sustainable oilseed processing. The investigation focused on how different production profiles (crude vegetable oil, refined oil, hydrogenated oil and margarine) affect electricity and water use in selected Polish processing plants. The collected data were first grouped with cluster analysis to identify similar operational cases. The clusters were then visualized with a Self-Organizing Map (SOM), producing a two-dimensional topological feature map. This analysis indicated a subset of data for which it was appropriate to build predictive models of electricity and water consumption. Multi-layer perceptron (MLP) neural networks yielded highly accurate predictions of electricity (R² = 0.967 on the test set) and water (R² = 0.967 on the test set) use in oilseed processing. The resulting models can assist in selecting the most energy- and water-efficient processing configuration.

The study aims to explore the application of the Model Mismatch Strategy (MMS) to improve the speed control accuracy of a prototype rotarod apparatus (RRA), a device used to assess motor coordination in laboratory rodents. Two test scenarios were prepared: one taking into account the step change...

The paper describes the implementation of a PI controller autotuning procedure based on the doublet-pulse method. The doublet-pulse method is used as a tool to identify the control object. Its main advantage is its simplicity, requiring only two parameters to be declared, i.e., the amplitude and...

Fruit and vegetable processing comes 6th in terms of energy consumption in the agri-food industry. At the same time, 88.4% of the industry’s final energy consumption structure is thermal energy, which depends heavily on electricity consumption. In addition, fruit and vegetable processing has a significant impact on the environment due to consumption of significant amounts of water. Reducing these three indicators simultaneously would increase the efficiency of the process while improving environmental protection. This paper proposes neural models of thermal energy, electricity and water consumption for selected major fruit- and vegetable-processing plants in Poland. These models were the basis for formulating a multi-criteria optimization task. Optimization of thermal energy, electricity and water consumption was carried out using genetic algorithms. The optimization results in the sense of Pareto can be the basis for the use of sustainable technology in selected fruit- and vegetable-processing plants.

Background: Neuropathic pain is drug-resistant to available analgesics and therefore novel treatment options for this debilitating clinical condition are urgently needed. Recently, two drug candidates, namely mirogabalin and cebranopadol have become a subject of interest because of their potential utility as analgesics for chronic pain treatment. However, they have not been investigated thoroughly in some types of neuropathic pain, both in humans and experimental animals. Methods: This study used the von Frey test, the hot plate test and the two-plate thermal place preference test supported by image analysis and machine learning to assess the effect of intraperitoneal mirogabalin and subcutaneous cebranopadol on mechanical and thermal nociceptive threshold in mouse models of neuropathic pain induced by streptozotocin, paclitaxel and oxaliplatin. Results: Mirogabalin and cebranopadol effectively attenuated tactile allodynia in models of neuropathic pain induced by streptozotocin and paclitaxel. Cebranopadol was more effective than mirogabalin in this respect. Both drugs also elevated the heat nociceptive threshold in mice. In the oxaliplatin model, cebranopadol and mirogabalin reduced cold-exacerbated pain. Conclusions: Since mirogabalin and cebranopadol are effective in animal models of neuropathic pain, they seem to be promising novel therapies for various types of neuropathic pain in patients, in particular those who are resistant to available analgesics.

Magnetorheological (MR) dampers are controlled energy-dissipating devices utilizing smart fluids. They operate in a fast and valveless manner by taking advantage of the rheological properties of MR fluids. The magnitude of the response of MR fluids, when subjected to magnetic fields, is of sufficient magnitude to employ them in various applications, namely, vibration damping, energy absorption, exoskeletons, etc. At the same time, predicting their response to arbitrary mechanical and electrical inputs is still a research challenge. Due to the non-linearities involved in material properties or the design of the solenoid used for activating the fluid modeling the relationships between the control circuit and the material’s response is complex. Modeling studies can be classified into two categories. The parametric approach requires the knowledge of the internal material’s properties and takes advantage of physics formulas to infer the I/O relationships present in the damper. For comparison, the non-parametric approach harnesses various data mapping techniques to describe the device’s behavior. While the latter is more suited for design studies, the former seems ideal for control algorithm prototyping and the like. In this study, based on the so-called Support Vector Method (SVM), the authors develop a non-parametric model of the control circuit of an exemplary rotary MR damper. To the best of the author’s knowledge, it is the first attempt at an SVM application for MR dampers’ control circuit modeling. Using the acquired experimental data, the I/O relationships are inferred using the SVM algorithm, and its performance is verified across a wide range of excitation frequencies. The obtained results are satisfactory, and the current response of the MR damper is well-predicted. The model performance shows the potential for incorporating it into model-based prototyping and designing of MR control systems.

The antitumor drug, oxaliplatin, induces neuropathic pain, which is resistant to available analgesics, and novel mechanism-based therapies are being evaluated for this debilitating condition. Since activated microglia, impaired serotonergic and noradrenergic neurotransmission and overexpressed sodium channels are implicated in oxaliplatin-induced pain, this in vivo study assessed the effect of minocycline, a microglial activation inhibitor used alone or in combination with ambroxol, a sodium channel blocker, or duloxetine, a serotonin and noradrenaline reuptake inhibitor, on oxaliplatin-induced tactile allodynia and cold hyperalgesia. To induce neuropathic pain, a single dose (10 mg/kg) of intraperitoneal oxaliplatin was used. The mechanical and cold pain thresholds were assessed using mouse von Frey and cold plate tests, respectively. On the day of oxaliplatin administration, only duloxetine (30 mg/kg) and minocycline (100 mg/kg) used alone attenuated both tactile allodynia and cold hyperalgesia 1 h and 6 h after administration. Minocycline (50 mg/kg), duloxetine (10 mg/kg) and combined minocycline + duloxetine influenced only tactile allodynia. Seven days after oxaliplatin, tactile allodynia (but not cold hyperalgesia) was attenuated by minocycline (100 mg/kg), duloxetine (30 mg/kg) and combined minocycline and duloxetine. These results indicate a potential usefulness of minocycline used alone or combination with duloxetine in the treatment of oxaliplatin-induced pain.

Background: Wide use of oxaliplatin as an antitumor drug is limited by severe neuropathy with pharmacoresistant cold hypersensitivity as the main symptom. Novel analgesics to attenuate cold hyperalgesia and new methods to detect drug candidates are needed. Methods: We developed a method to study thermal preference of oxaliplatin-treated mice and assessed analgesic activity of intraperitoneal duloxetine and pregabalin used at 30 mg/kg. A prototype analgesiameter and a broad range of temperatures (0–45 °C) were used. Advanced methods of image analysis (deep learning and machine learning) enabled us to determine the effectiveness of analgesics. The loss or reversal of thermal preference of oxaliplatin-treated mice was a measure of analgesia. Results: Duloxetine selectively attenuated cold-induced pain at temperatures between 0 and 10 °C. Pregabalin-treated mice showed preference towards a colder plate of the two used at temperatures between 0 and 45 °C. Conclusion: Unlike duloxetine, pregabalin was not selective for temperatures below thermal preferendum. It influenced pain sensation at a much wider range of temperatures applied. Therefore, for the attenuation of cold hypersensitivity duloxetine seems to be a better than pregabalin therapeutic option. We propose wide-range measurements of thermal preference as a novel method for the assessment of analgesic activity in mice.