The problem of synthesizing the parameters of the drive control system of the responsible unit of the construction 3D printer - the screw dispenser of the print head using the method of neuro-fuzzy control is considered. An algorithm for building an intelligent drive control system is described. A training sample is obtained from the data of variables determined as a result of modeling the automatic system control with a continuous proportional-integral-differentiating (PID) regulator. Training of a neuro-fuzzy output system in the MATLAB software environment is performed using the hybrid method a. Transient characteristics of the control system with continuous and neuro-fuzzy proportional-differentiating (PD) regulator are obtained. Direct indicators of the quality of the considered control systems are determined, and an analysis of these results is carried out. The use of neuro-fuzzy control of the screw doser drive of the 3D printer print head made it possible to obtain the desired a transient process confirmed as a result of a computational experiment.

Keywords: 3D printer, screw dispenser drive, print head, concrete mix, transfer function, proportional-integral-differentiating controller, neuro-fuzzy output system

The article discusses the use of algorithms based on artificial neural networks when working with non-stationary signals, in particular biomedical ones, such as an electroencephalograph signal, to identify and process local signal features. The use of conventional patch electrodes for EEG recording leads to the appearance of noise and requires special signal processing. For this, bandpass wavelet filtering is used. The obtained data are further processed using an artificial neural network to identify information contained in a limited interval in the biomedical signal. To train the neural network, the Levenberg-Marquardt method was used, as the optimal one and meeting the requirements.

Keywords: artificial neural network, electroencephalography, wavelet filtration, biomedicine, non-stationary signal, system analysis

In the presented work, a method of reconstruction of structural images in endoscopic optical coherence tomography based on taking into account speckle patterns by using the operations of morphological erosion and expansion is considered. The proposed algorithm for reducing the level of speckle noise to improve the quality of visualization in endoscopic optical coherence tomography was practically implemented in the LabVIEW environment. Distinctive features of the proposed algorithm are morphological processing of B-scans, filtering by convolution before morphological processing of B-scans, and multilevel filtering of A-scans and B-scans consisting of them. A series of computer experiments showed a stable increase in the signal-to-noise ratio and contrast of the obtained structural images when using the developed algorithm. The proposed algorithm for reducing the level of speckle noise in structural images can be used in medical technologies to visualize the internal structure of cavities and body tracts.

Keywords: speckle noise, optical coherence tomography, endoscopic systems, structural image, morphological erosion, morphological dilation, speckle reduction, coherence probing depth

An algorithm for numerical simulation of optical structure disturbance of biomedical objects is described. The key features of the presented algorithm are: posterization of CT or MRI scans, subsequent encoding and manual identification of each biological tissue, assigning it tabular optical properties. The described algorithm can be used in diffuse optical tomography (DOT) for numerical simulation of optical properties of biomedical objects of their constituent with variable spatial resolution. Numerical simulation showed that the presented algorithm allows us to describe the optical structure of biological tissue with data validity >90%.

Keywords: optical properties of biological tissues, time-resolved diffuse optical tomography, forward problem, turbid media, posterization