Search

The comparison of heat losses by pipelines of an extensive residential neighborhood heating system for two options of the distribution network was carried out for a residential neighborhood in Kharkov. The proposed configuration of the heating network differs from the existing ("basic") one in using of the law of heating medium flow rate variation along the heat pipe length. This law takes into account increased flow rate of heating water through branches at the initial sections of the pipeline. The actual flow rate distribution is approximated by a step function. The difference in the laws of flow rate variation is taken into account by the exponent value. The calculation of heat losses was carried out for underground pipelining in non-accessible tunnels. The temperature of heat line water is taken to be the corresponding to the design outdoor air temperature for heating according to the temperature schedule of the heating network. Specific heat losses by pipelines in heat network sections are considered to be at the standard level for non-accessible tunnels. The soil temperature at the depth of the heat pipe axis is taken equal to 5°C. Heat losses by the structural elements of the heat network are taken into account by a factor of 1.15. The variation of the flow rate and temperature of network water in rated pipeline sections is considered in the analysis. The water flow rate at the sections was found based on the design thermal loads of connected buildings. It is shown that when choosing the configuration of the distribution network of the heating system of a group of buildings, preference should be given to the option with a lower value of the exponent in the equation for heating medium flow rate variation along the length of the main line of the network. For extensive heating networks, this can be achieved by connecting as many buildings as possible to the heating network sections close to a heat supply station. An increase in the network water flow rate through the branches at the initial sections of the pipeline ensures a decrease in heat losses by the network pipelines. For the considered part of a residential neighborhood, the decrease in heat loss at the design outdoor air temperature for heating is 5.5 %., На прикладі житлового мікрорайону м. Харкова проведено порівняння втрат теплоти трубопроводами розгалуженої мікрорайонної системи опалення для двох варіантів виконання розподільної мережі. Запропонований варіант конфігурації теплопроводів відрізняється від існуючого («базового») законом зміни витрат теплоносія по довжині теплопроводу, для якого характерний підвищений рівень витрат мережної води через відгалуження на початкових ділянках гілки. Фактичний розподіл витрат теплоносія апроксимований ступеневим законом. Відмінність законів зміни витрат враховано величиною показника ступеня. Обчислення теплових втрат проведено для умов підземної прокладки трубопроводів у непрохідних каналах. Температуру мережної води прийнято відповідно до розрахункової для опалення температурі зовнішнього повітря за температурним графіком теплової мережі. Питомі втрати теплоти трубопроводами на ділянках мережі прийнято на рівні нормативних значень для вказаного способу прокладки. Температуру ґрунту на глибині вісі теплопроводу прийнято рівною 5 оС. Втрати теплоти конструктивними елементами мереж враховано коефіцієнтом 1,15. Обчислення проведено з урахуванням зміни витрат і температури мережної води на розрахункових ділянках. Витрати мережної води на ділянках мережі визначено за проектними тепловими навантаженнями приєднаних будівель. Показано, що при виборі конфігурації розподільної мережі системи опалення групи будівель перевагу слід надавати варіанту з меншим значенням показника ступеня у рівнянні зміни витрат теплоносія по довжині головної гілки мережі. В умовах розгалужених теплових мереж це досягається приєднанням якомога більшої кількості будівель до найближчих до центрального теплового пункту ділянок розподільної теплової мережі. Збільшення витрат мережної води через відгалуження на початкових ділянках гілки забезпечує зменшення теплових втрат трубопроводами мережі. Для розглянутого фрагменту житлового мікрорайону зменшення втрат теплоти при розрахунковій для опалення температурі зовнішнього повітря становить приблизно 5,5 %.

Bayesian optimisation is a sample-efficient search methodology that holds great promise for accelerating drug and materials discovery programs. A frequently-overlooked modelling consideration in Bayesian optimisation strategies however, is the representation of heteroscedastic aleatoric uncertainty. In many practical applications it is desirable to identify inputs with low aleatoric noise, an example of which might be a material composition which consistently displays robust properties in response to a noisy fabrication process. In this paper, we propose a heteroscedastic Bayesian optimisation scheme capable of representing and minimising aleatoric noise across the input space. Our scheme employs a heteroscedastic Gaussian process (GP) surrogate model in conjunction with two straightforward adaptations of existing acquisition functions. First, we extend the augmented expected improvement (AEI) heuristic to the heteroscedastic setting and second, we introduce the aleatoric noise-penalised expected improvement (ANPEI) heuristic. Both methodologies are capable of penalising aleatoric noise in the suggestions and yield improved performance relative to homoscedastic Bayesian optimisation and random sampling on toy problems as well as on two real-world scientific datasets. Code is available at: \url{https://github.com/Ryan-Rhys/Heteroscedastic-BO}, Published in Machine Learning: Science and Technology 2021 (https://iopscience.iop.org/article/10.1088/2632-2153/ac298c) Earlier version accepted to the 2019 NeurIPS Workshop on Safety and Robustness in Decision Making

Reducing energy consumption is a major challenge for "energy-intensive" industries such as papermaking. A commercially viable energy saving solution is to employ data-based optimization techniques to obtain a set of "optimized" operational settings that satisfy certain performance indices. The difficulties of this are: 1) the problems of this type are inherently multicriteria in the sense that improving one performance index might result in compromising the other important measures; 2) practical systems often exhibit unknown complex dynamics and several interconnections which make the modeling task difficult; and 3) as the models are acquired from the existing historical data, they are valid only locally and extrapolations incorporate risk of increasing process variability. To overcome these difficulties, this paper presents a new decision support system for robust multiobjective optimization of interconnected processes. The plant is first divided into serially connected units to model the process, product quality, energy consumption, and corresponding uncertainty measures. Then multiobjective gradient descent algorithm is used to solve the problem in line with user's preference information. Finally, the optimization results are visualized for analysis and decision making. In practice, if further iterations of the optimization algorithm are considered, validity of the local models must be checked prior to proceeding to further iterations. The method is implemented by a MATLAB-based interactive tool DataExplorer supporting a range of data analysis, modeling, and multiobjective optimization techniques. The proposed approach was tested in two U.K.-based commercial paper mills where the aim was reducing steam consumption and increasing productivity while maintaining the product quality by optimization of vacuum pressures in forming and press sections. The experimental results demonstrate the effectiveness of the method.

This article proposes an Enhanced Memetic Differential Evolution (EMDE) for designing digital filters which aim at detecting defects of the paper produced during an industrial process. Defect detection is handled by means of two Gabor filters and their design is performed by the EMDE. The EMDE is a novel adaptive evolutionary algorithm which combines the powerful explorative features of Differential Evolution with the exploitative features of three local search algorithms employing different pivot rules and neighborhood generating functions. These local search algorithms are the Hooke Jeeves Algorithm, a Stochastic Local Search, and Simulated Annealing. The local search algorithms are adaptively coordinated by means of a control parameter that measures fitness distribution among individuals of the population and a novel probabilistic scheme. Numerical results confirm that Differential Evolution is an efficient evolutionary framework for the image processing problem under investigation and show that the EMDE performs well. As a matter of fact, the application of the EMDE leads to a design of an efficiently tailored filter. A comparison with various popular metaheuristics proves the effectiveness of the EMDE in terms of convergence speed, stagnation prevention, and capability in detecting solutions having high performance.