Modern neural networks have made great strides in recognising objects in images and are widely used in defect detection. However, the output of a neural network strongly depends on both the training dataset and the conditions under which the image was acquired for analysis. We have developed a software–hardware method for evaluating the effect of variable lighting on the results of defect recognition using a neural network model. The proposed approach allows us to analyse the recognition results of an existing neural network model and identify the optimal range of illumination at which the desired defects are recognised most consistently. For this purpose, we analysed the variability in quantitative parameters (area and orientation) of damage obtained at different degrees of illumination for two different light sources: LED and conventional incandescent lamps. We calculated each image’s average illuminance and quantitative parameters of recognised defects. Each set of parameters represents the results of defect recognition for a particular illuminance level of a given light source. The proposed approach allows the results obtained using different light sources and illumination levels to be compared and the optimal source type/illuminance level to be figured out. This makes implementing a defect detection environment that allows the best recognition accuracy and the most controlled product quality possible. An analysis of a steel sheet surface showed that the best recognition result was achieved at an illuminance of ~200 lx. An illuminance of less than ~150 lx does not allow most defects to be recognised, whereas an illuminance larger than ~250 lx increases the number of small objects that are falsely recognised as defects.

The researches results of the energy and dynamic characteristics for FYL-3014 and ARPL-1W LEDs with different spectral radiation when voltage rectangular pulses feds to LEDs are presented in the paper. On the basis of obtained oscilograms it is established that electrical circuits of pulsed supply of the LEDs contain hidden reactive elements of inductive and capacitive nature. The substitution schemes are proposed for these circuits and their parameters have been determined. In substitution schemes that are proposed for these circuits the LED is represented by a parallel RC link, the active component of which is determined by the heterojunction's active region resistance, and the reactive one by a capacity that is equal diffuse capacity of transition. On the basis of analysis of obtained transient processes equations for these circles it established the attenuation coefficient's dependence on the resistance of the heterojunction's active region. The influence of pulse frequency on the LEDs energy efficiency has been investigated. It is established that the maximum pulse frequency of the FYL-3014 and ARPL-1W LEDs is equal 700 kHz. References 12, figures 6.

Напівпровідникові джерела світла охоплюють різні сфери застосування від зовнішнього і побутового освітлення до дисплеїв комп’ютерних систем та портативної електроніки, від світлових приладів автомобілів до опромінювальних систем в аграрному секторі. У всіх цих середовищах їх виділяє висока енергетична ефективність, спрощена система живлення та керування. Щоб уникнути коливань світлового потоку при постійному струмі живлення і великій крутизні ВАХ прямого зміщення діода, виникає необхідність стабілізації струму, що приводить до додаткових енергетичних затрат та ускладнень системи керування світловим потоком. Перевагу отримують імпульсні системи живлення з широтною модуляцією імпульсів (ШІМ). В даній статті проведено аналіз параметрів системи ШІМ-живлення однополярними імпульсами прямокутної форми та залежності світлового потоку при їх зміні. Встановлено, що при струмах інжекції 0,43 – 1,45 мА світловий потік лінійно зростає з коефіцієнтом k=0,179, що пояснюється мономолекулярним механізмом рекомбінації. При подальшому збільшенні струму інжекції, спостерігається нелінійне зростання світлового потоку, що описується поліномом третього порядку.

In recent years, there has been a growing trend in the use of solar and wind energy for electricity generation. This shift is primarily driven by the global need to reduce greenhouse gas emissions and combat climate change. However, the increasing share of renewable energy sources without the provision of adequate flexible generation or energy buffering, capacity may lead to a range of unforeseen technical and systemic consequences. These may include technological disruptions in the operation of the entire power grid or significant portions of it. One of the key strategies to mitigate such adverse effects is the deployment of energy storage systems. These systems enable efficient management of energy flows during the processes of generation, storage, and discharge of electricity into the grid, as well as the regulation and control of power system operations. Electrical energy storage systems are technologies designed to retain energy for later use. Each storage technology possesses unique characteristics that contribute to more efficient energy distribution and help meet demand across various energy supply sectors. Their implementation opens new opportunities for improving the quality of operational control and optimizing the performance of energy systems. This paper provides a review of the most commonly used types of energy storage systems employed in power systems and offers a comparative analysis of their key characteristics. Furthermore, an attempt is made to analyze the main categories of energy storage technologies based on their storage method, energy type, storage duration, and capacity. The findings of this study support the preliminary selection of a suitable type of energy storage system, depending on the specific characteristics and parameters of the energy system in which it is to be applied.