Electrotechnical Institute

To explore the potential of generative artificial intelligence in electrical machine inverse design, this paper focus on database development as preparation for model fine-tuning and agents developing. A framework is proposed to construct the database spanning a wide range of power ratings, characterized by geometric similarity, using surface-mounted permanent magnet machines as a case study. Python-driven interactions between finite element analysis and optimization algorithms facilitate this process. Scaling and correlation factors are used as variables for finite element model construction and key performance indexes evaluation under multi-physics considerations. These factors, paired with key performance indexes, form the sample set in a single cycle. A metamodel of optimal prognosis based surrogate model is trained using 500 samples collected via Latin hypercube sampling within 23 hours, mapping factors to key performance indexes. Using this surrogate model, a genetic algorithm generates 9900 scaling designs in 10 minutes. 16 designs on the predicted pareto front were validated by finite element analysis, showing strong alignment with predictions and confirming the effectiveness of the proposed framework. Further, 4 designs were directly retrieved from the database to meet the given specifications, with No. 78, No. 3501 verified by finite element analysis showing deviations within 10 %. This demonstrates a method in inverse design, eliminating the need for time-consuming fine-tuning to satisfy specifications.

The introduction of closed-loop mechanisms has significantly enhanced the performance of interferometric fiber optic gyroscopes (IFOGs). However, the poor scale factor (SF) stability limits its further application due to the use of broadband light sources. This study first reviewed the impact of the average wavelength of a light source on SF stability in a closed-loop IFOG setup. A simulation model is developed according to modulation and demodulation principles, and the SF error is found to be proportional to the wavelength drift in a closed-loop IFOG. Additionally, employing a laser with a more stable average wavelength instead of a super fluorescent fiber source (SFS) for driving the IFOG enhanced the SF stability by an order of magnitude to 0.38 ppm in ambient-air experiments, which is one of the best SF performances achieved thus far. With the significant improvement in stability during the variable temperature tests, the IFOG measures rotation rates more accurately.

The use of more advanced electric motor protection devices, that are able not only to record, but also to predict the achievement of dangerous values the leakage current, makes it possible to warn and inform in advance about a possible danger for service personnel. Most often, neural networks are used to solve this problem. On the basis the obtained experimental data, neural networks were synthesized, both on the basis technological parameters and on the basis theory of time series forecasting. A comparison of the operating features of a neural network based on technological parameters and a neural network based on the theory of time series forecasting indicates that: the first type of neural network works more efficiently with sharp emissions of the predicted leakage current; the second type of neural networks more accurately models the value of the predicted value near its relatively averaged readings. The forecasting features these neural networks proved the feasibility of combining them into a single intelligent block with the possibility of choosing the best forecast at a certain point in time.

Быстро затвердевшие ленты на основе сплава Al74Cu16Mg10 были получены методом спиннингования. Для получения кристаллической структуры быстрозатвердевшие ленты отжигали в атмосфере аргона. Аморфная и нанокристаллическая структура подтверждена анализами XRD и TЕM. Исследовано влияние легирующих элементов Zn и Zr на коррозионное поведение быстрозатвердевшего сплава Al74Cu16Mg10 в аморфных и нанокристаллических аналогах. Проведены гравиметрические испытания на общую коррозию при 25 °С и 50 °С в среде 3,5% NaCl. При 25 °С скорость коррозии аморфных сплавов оказалась в 1,5–4 раза ниже скорости коррозии их кристаллических аналогов. Влияние трансформации аморфной структуры в нанокристаллическую на скорость коррозии при 50 °С отрицательно и наиболее существенно в Zn-содержащем сплаве. Проведены электрохимические испытания на общую и локальную коррозию в среде 3,5% NaCl и объяснен гальванический механизм локальной коррозии в сплавах. Основной причиной регистрируемой повышенной локальной коррозии кристаллических сплавов является химическая и структурная неоднородность, связанная с наличием в алюминиевой матрице активных интерметаллических фаз Al2CuMg, Al2 (Cu, Zn), Al3Zr4. Обсуждается влияние неровности поверхности, структуры слоя продуктов коррозии, отложенного на поверхность металла, и отжига для трансформации аморфной структуры на коррозионное поведение сплавов.

The problem of joint use of three criteria for testing the hypothesis of uniformity and normality is considered: Frotsini (1978), Ali – Chergo – Revis (1992) and a differential version of the Frotsini test (2016). Materials and methods. It is proposed to match each of the studied criteria with an equivalent artificial neuron. Then a neural network of three binary neurons gives a three-bit output code. A network of ternary neurons will produce a six-bit output code. Redundant output codes of neural networks can be convolved with error correction. Results. It is shown that binary artificial neurons make it possible to distinguish between small samples of 16 experiments with a normal or uniform distribution with the same probabilities of errors of the first and second kind – 0,031. Ternary neurons give the same probabilities of errors of the first and second kind at the level of – 0,2303. Due to the independence of the data (Hamming distance spectra do not overlap), it is possible to reduce the error probability to a value of – 0,007. Conclusions. Known code structures with redundancy, capable of detecting and correcting errors, were created mainly for binary codes. Ternary code constructions are poorly studied. It is necessary not only to develop a branch of ternary self-correcting codes, but also a code superstructure that combines binary and ternary neural network self-correcting structures.

Today, energy is a vital component in the functioning of a hospital. Hospital technical facilities have several types of technologies, these include appliances for use; examination apparatus. So, for Quality Health Care in a hospital, there is a need to ensure the proper functioning of hospital equipment. In addition to the required maintenance as specified by the device manufacturer, the quality of the electrical energy across the device must be ensured. This article is an analysis of the quality of electric energy at the substation of National Hospital of Niamey. Thereby, the data collection, followed by the data processing and analysis revealed the parameters characterizing the quality of electrical energy across the substation. Our studies have shown that the substation is underutilized as the maximum inrush current is less than half the available current. The current was consumed by the three phases has resulted in a strong current unbalance (230 A). However, the current unbalance and the voltage amplitude, are admissible accordingly base on EN50160 standard. Furthermore, the harmonics voltages present in this medium are in the accepted range (1.8%) according to IEEE 519 standard. However, the fundamental frequency does not meet the standard, but the difference obtained has no adverse effect.