The problem of image recognition using methods based on statistical solutions can be divided into two classes: parametric and nonparametric. In the first case there is a set of data on the selection of image criteria, in the second such criteria must be found. Taking into account, the possibilities of obtaining initial data for the identification of agricultural objects, the first option is considered in the article. Possibilities of diagnostics of strawberry growth at a stage of its cultivation in hothouse conditions are presented. Several image classifiers that can be used to solve such problems are investigated. An experiment was performed, which has shown the accuracy of the applied algorithms for diagnosis and recognition of berries, which allowed to set thresholds for the detection of ripe berries. A number of berry recognition methods were compared in order to study the accuracy of berry recognition and response to berry growth.

У статті представлено можливості дистанційного вимірювання робочих характеристик електродвигунів з використанням індуктивних датчиків переміщень. Висвітлено можливості обробки сигналів на основі операційних підсилювачів. В результаті аналізу можливостей індуктивних датчиків переміщень та схем підсилення на інвертуючих операційних підсилювачах, було запропоновано інтерфейс, який можна застосовувати для дистанційних вимірювань обертальних моментів електродвигунів.

The article investigates the methods and means of measuring the operating characteristics of elec-tric generators, namely the output voltage, resistance, frequency, current and torque. The analysis of literature sources that characterize the structural elements and the principle of operation of synchro-nous generators is carried out. Methods of measuring the operating characteristics of electric genera-tors are studied. Mathematical models that describe the relationships between physical quantities that characterize the parameters of electric generators are considered. The estimation of modern direc-tions of development of means of measurement of torques of electric generators is carried out. Meth-ods of data processing and visualization obtained by primary devices are studied. The dependence of the torque of electric generators and their output parameters is studied. A block diagram of a digital measuring sensor is constructed, which shows the main components of a device for measuring torque using an inductive sensor. Based on research, a method for measuring torque using an inductive sensor has been proposed, which allows increasing the sensitivity of the measurement by improving the metrological characteris-tics of the measuring channel. This improvement is that the coils that change their inductance under the action of torsional load on the motor shaft are not affected by electromagnetic interference created by the generator during operation. Simulation of the electrical circuit using the proposed method al-lowed to obtain the attenuation coefficient of the in-phase signal 80 dB at an input signal frequency of 10 kHz, thus providing high sensitivity. This model was tested, which made it possible to obtain errors in the simulation in the operating mode. The standard deviation and the absolute measurement error are determined. The Matlab / Simulink modeling complex was used to process the measurement results and study the errors, which allowed visualizing the transient characteristics of the measuring signal and obtain a possible error.

У статті досліджуються методи підвищення точності вимірювальних приладів. Розглядаються причини виникнення похибок, а також способи їх ідентифікації. Проводиться аналіз методів зменшення похибок та їх корегування. Досліджуються програмно-апаратні способи мінімізації похибок вимірювальних приладів, які виникають у вимірювальних каналах. На основі дослідження існуючих методів корекції похибки, здійснено моделювання вимірювального каналу для перетворювача обертального моменту електродвигуна та проведено аналіз результатів. На підставі отриманих даних розроблено рекомендації щодо застосування вимірювальних перетворювачів в залежності від вимірювальних потреб та умов застосування.

The article analyzes the influence of different types of probe geometry of a scanning probe microscope (SPM) on the features of measuring the surface topography of a nano-object. Based on the analysis, it was determined that the main drawback inherent in all modes of scanning probe microscopy is the finite size of the measuring probe tip, which cannot reach certain areas of the measuring surface during scanning, which is caused by the geometric characteristics of the probe shape. This leads to a significant deterioration of the spatial resolution and significant distortions in the SPM images when scanning surfaces with large unevenness of the ratio between the typical vertical and horizontal dimensions. Based on the conducted research, the methods of restoration of SPM images are proposed, which are built on mathematical and computer processing of SPM data, which takes into account the specific shape of the probe tip and allows improving the metrological characteristics of the measurement information. It is proved that the SPM image and the experimentally obtained shape of the tip are two-dimensional arrays of discrete values, for which the derivative is an incorrectly determined value. It is recommended that instead of deriving discrete functions during the numerical deconvolution of SPM images, during scanning with a constant average height, use the requirement for the minimum distance of the tip to the surface. It has been proven that the most effective way of digital correction of the surface topography is numerical deconvolution using the tip image obtained experimentally by scanning test structures with a well-known topography and subsequent computer processing of the data. A method of partial restoration of the topography is proposed, which is characterized by flexibility to the set metrological tasks and is aimed at increasing the speed of computing operations while ensuring the necessary accuracy of measurement information.