scholarly journals Neural networks application in managing the energy efficiency of industrial enterprise

2019 ◽  
Vol 7 (1) ◽  
pp. 62-73 ◽  
Author(s):  
Svitlana Klepikova
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Energy Efficiency ◽  
Energy Intensity ◽  
Machine Building ◽  
Industrial Enterprise ◽  
Practical Implementation ◽  
Network Synthesis ◽  
Acceptable Error ◽  
Industrial Enterprises

The article is devoted to the creation of a method for using of neural networks approach in solving problems of energy efficiency management at the industrial enterprise. The method allows to obtain an approximate expected value of the energy intensity of production, depending on the values of the main factors affecting it. The multilayer perceptron was chosen as the type of neural network, synthesis of which was carried out by using the genetic algorithm. When sampling for the synthesis of a neural network, we used the results that were obtained by means of a priori ranking, correlation and regression analysis based on the statistical data of industrial enterprises in machine-building profile. The recommendations of the use of the method and the application of its results in the practical implementation at the industrial enterprise are given. Calculations based on the aforementioned method ensured a high precision of prediction of energy intensity values for industrial enterprises that were included in the sample during the synthesis of the neural network, and an acceptable error while testing on industrial enterprises from a test sample.

scholarly journals Methodic tools to optimize marketing expenses of the innovatively active industrial enterprises in Ukraine

2016 ◽  
Vol 14 (1) ◽  
pp. 44-50 ◽  
Author(s):  
Oleg Olefirenko
Keyword(s):  
Mathematic Model ◽  
Machine Building ◽  
Practical Implementation ◽  
Industrial Enterprises ◽  
Managerial Decisions ◽  
Production Distribution ◽  
Market Situation ◽  
The Given ◽  
Rational Process

The efficient sales policy of the machine building innovatively active enterprises is connected with its rational process financing. Optimal determination of innovative production distribution expenses is top-priority element to increase economic subject’s activity profitability and to increase its competitive positions at the market. Thus, planning of costs for innovatively active machine building enterprises sales has to be based on economic and rationally adaptive mathematic tools to industrial enterprises activity specific. Practical implementation of the mentioned task is possible owing to economic and mathematic model to plan costs for innovatively active enterprises production, which preconditions urgency of the given research. Besides the tools investigation is also urgent and it allows to foresee future expenses amounts for sales, demand for production and profit of the innovatively active industrial enterprise, behavior in future depending on market situation. The article deals with scientific and methodic approach to optimize distribution expenses of the innovatively active industrial enterprises in Ukraine. Economic and mathematic modeling methods allowed to formalize models to plan distribution expenses of innovatively active enterprise, demand and profits, that is prerequisite to form prognostications by proper directions. Practical implementation of the suggested scientific and methodic approach on the example of machine building enterprise in Ukraine results in confirmation of models correspondence and establishment of inefficiency to distinguish expenses. It gives evidence about necessity to optimize expenses of enterprise and to introduce active managerial decisions concerning its activity profitability growth

IMPROVEMENT OF THE MARKETING COMPLEX OF THE INDUSTRIAL ENTERPRISE

2021 ◽  
Vol 298 (5 Part 1) ◽  
pp. 190-194
Author(s):  
Olena Moroz ◽  
Kostiantyn Latyshev ◽  
Oksana Zbyrannyk ◽  
Keyword(s):  
Machine Building ◽  
Industrial Enterprise ◽  
Economic Conditions ◽  
Competitive Advantages ◽  
Highly Qualified ◽  
Marketing Environment ◽  
Industrial Enterprises ◽  
Qualified Personnel ◽  
Satisfaction Of Needs ◽  
Simple Reduction

This article considers the issues on improvement of marketing complex of industrial enterprise, with the purpose of stabilization of its activity and strengthening of competitive positions. It is proposed to improve the activities of industrial enterprises on the basis of the formation of measures that will ensure the current support of domestic enterprises in difficult economic conditions. One of the ways of improving the performance of the company is to change the model “4P” into a model of marketing complex “5P” and use personnel (“Personal”) as one of the tools. On the basis of the conducted research the influence of external environment factors was evaluated on the basis of the model of the marketing complex “4P”. As a result, it was found that the surveyed company has low competitive advantages, but these competitive advantages may not be valid without preservation of highly qualified personnel, because of the instability of the activities of the company, constant differences in production, simple, reduction of workers or voluntary migration of manpower and as a result of the loss of highly qualified workers and the position of the leader in the field of machine building. The evolution of the marketing complex depending on the influence of factors of the marketing environment is examined. The application of the marketing complex not only contributes to satisfaction of needs of potential organizations in the framework of target markets, but also allows maximizing the efficiency of industrial enterprises’ activity. Practical relevance of the research carried out in the article lies in the fact that using recommendations and directions of upgrading the marketing complex of industrial enterprise will ensure stabilization of its activity on the market due to the influence of regressive external factors.

scholarly journals Financial and Economic Features of Technical Re-equipment of the Workshop Machine-Building Enterprise

2020 ◽  
Vol 11 (5) ◽  
pp. 434
Author(s):  
Elvira Distantovna Khisamova ◽  
Svetlana Mazgutovna Nuryyakhmetova ◽  
Gulnara Damirovna Kayumova
Keyword(s):  
Energy Intensity ◽  
New Product ◽  
Machine Building ◽  
Production Equipment ◽  
Technical Development ◽  
Industrial Enterprises ◽  
Fixed Assets ◽  
Technological Level ◽  
Different Levels

One of the urgent problems of modern industrial enterprises is the problem of their technical development. The most common direction of technical development is the technical re-equipment of industrial enterprises. This is a very long and costly process, requiring both from the management of the enterprise and from its employees of high qualification, the ability, and skills to make quick decisions and predict the outcomes of these decisions. Currently, the market for technical and technological equipment is represented by many kinds of different industrial machines, aggregates, mechanisms of different manufacturing firms, different levels of complexity, productivity, energy intensity, and, of course, different costs. The analysis of the market, the choice of suppliers of production equipment, the formulation of terms of delivery and payment, installation, assembly, and installation of equipment at the enterprise, commissioning and subsequent technical support are all elements of the process of renewal of fixed assets called technical re-equipment.Technical re-equipment includes raising the technological level of production, which includes the use of additional new equipment (both in the case of physical and moral obsolescence).During this event, either modified tools will be used in the production of old products, or the quality of the products will change, or a completely new product will be produced, or all taken together. In addition, the concept of technical re-equipment can include the re-qualification of personnel during the re-equipment process and bringing technologies in line with environmental norms and standards.

An Analysis on Carbon Emissions and Energy Efficiency of Small Heavy Industrial Enterprises in Shanghai

2013 ◽  
Vol 869-870 ◽  
pp. 997-1000
Author(s):  
Jing Jing Zhang ◽  
Jian Cheng Kang ◽  
Hao Zhang
Keyword(s):  
Energy Efficiency ◽  
Energy Consumption ◽  
Carbon Emissions ◽  
Energy Intensity ◽  
Correlation Coefficients ◽  
Carbon Intensity ◽  
Small Enterprises ◽  
Growth Trend ◽  
Positive Correlation ◽  
Industrial Enterprises

Based on the energy consumption and the output value data of the 6 small heavy industrial enterprises during 2007-2011 in Shanghai, we calculated comprehensive energy consumption, carbon emissions, carbon intensity and energy intensity of these enterprises. It been found that the comprehensive energy consumption and the carbon emissions of the 6 small enterprises are in a fluctuating growth trend but the energy intensity and the carbon intensity show a trend of fluctuating downward. The energy intensity and the carbon intensity of the small enterprises are much larger than the average of the two whole industries in Shanghai. We analyzed the correlation coefficients between the output value and the energy consumption as well as between the output value and the carbon emissions. The results show that the comprehensive energy consumption and the carbon emissions have positive correlation as well as the carbon emissions and the output value.

scholarly journals Energy-efficient memcapacitor devices for neuromorphic computing

2021 ◽  
Author(s):  
Kai-Uwe Demasius ◽  
Aron Kirschen ◽  
Stuart Parkin
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Energy Efficiency ◽  
High Precision ◽  
Energy Efficient ◽  
Lateral Size ◽  
Data Intensive Computing ◽  
Data Intensive ◽  
Specialized Hardware

AbstractData-intensive computing operations, such as training neural networks, are essential for applications in artificial intelligence but are energy intensive. One solution is to develop specialized hardware onto which neural networks can be directly mapped, and arrays of memristive devices can, for example, be trained to enable parallel multiply–accumulate operations. Here we show that memcapacitive devices that exploit the principle of charge shielding can offer a highly energy-efficient approach for implementing parallel multiply–accumulate operations. We fabricate a crossbar array of 156 microscale memcapacitor devices and use it to train a neural network that could distinguish the letters ‘M’, ‘P’ and ‘I’. Modelling these arrays suggests that this approach could offer an energy efficiency of 29,600 tera-operations per second per watt, while ensuring high precision (6–8 bits). Simulations also show that the devices could potentially be scaled down to a lateral size of around 45 nm.

scholarly journals Improving the energy efficiency of sorting centers by identifying objects and digit-letter information with neural networks

2021 ◽  
Vol 279 ◽  
pp. 01017
Author(s):  
Evgeniy Ivliev ◽  
Pavel Obukhov ◽  
Viktor Ivliev ◽  
Denis Medvedev ◽  
Viktor Martynov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Energy Efficiency ◽  
Convolutional Neural Network ◽  
Electricity Consumption ◽  
Dynamic Objects

The article is devoted to the development and analysis of methods of identifying dynamic objects. A neural network with the architecture of SSD MobileNetV2 has been developed to solve the problem of detecting baggage tags and barcodes. Several approaches are considered to solve the problem of identifying digital-letter information: Tesseract, SSD InceptionV2, OpenCV and a convolutional neural network. The efficiency of the methods on real images was checked. It was concluded that electricity consumption can be reduced by 49.43%.

Efficiency of industrial enterprises energy services taking into account the environmental factor

2021 ◽  
pp. 64-72
Author(s):  
G. Myroshnychenko ◽  
Keyword(s):  
Energy Consumption ◽  
Energy Saving ◽  
Greenhouse Gas ◽  
Environmental Factor ◽  
Energy Intensity ◽  
Machine Building ◽  
Industrial Enterprise ◽  
Energy Resources ◽  
Energy Services ◽  
The Impact

Objective: to investigate the problem of environmentally friendly efficiency of energy services of an industrial enterprise in the management system of economic processes, which would be based on the assessment of financial, economic, social and environmental effects on the final activity of the industrial enterprise. Method. The following methods were used in the process of research: analysis and synthesis, logic, theoretical generalization, comparison, causation. Results. The article examines the environmental acceptability of energy production and energy consumption, which is the main component of energy security. The efficiency of energy consumption in Ukraine is analyzed. The total greenhouse gas emissions in the energy sector have been studied. It is determined that the total greenhouse gas emissions are divided into four key areas: energy generation; extraction and processing of energy resources; transport; for consumption. It is determined that the only relatively universal and comparable for international and regional comparisons indicator of energy efficiency and environmentally oriented economy is the indicator of energy intensity of GDP, taking into account purchasing power parity (PPS). The problem of efficient ecologically oriented use of energy resources for industry is substantiated. The dynamics of energy consumption of machine-building enterprises of Ukraine and their energy intensity are analyzed. It is determined that machine-building enterprises have a significant resource of energy saving, and hence a significant resource of reducing the negative impact on the environment, the implementation of which is possible primarily due to structural changes and does not require significant financial resources. It is substantiated that the service of the chief power engineer is engaged in development and implementation of measures on energy saving, energy saving and environmental protection at the enterprises. Based on the specifics of the functioning of the energy sector, a chain of influence of the efficiency of energy services on the efficiency of the industrial enterprise is formed. The peculiarity of the proposed chain is the real requirements for taking into account the impact of energy on the functioning of the enterprise as a whole and on the external environment in both forward and reverse directions. Scientific novelty. The proposed chain of influence of efficiency of energy services on efficiency of the industrial enterprise allows to position efficiency of energy economy of the industrial enterprise in the general system of formation of efficiency of the enterprise and to specify its components through financial and economic, social and ecological effect. Practical significance. The study proved the need to clarify by taking into account the impact of the energy service in the form of emissions, discharges and wastes, which allows you to manage the efficiency of the enterprise as a whole taking into account the efficiency triad (environmental, social, economic component). as a strategic priority for the development of Ukraine. Key words: environmental factor, energy resources, energy intensity, environmental safety, energy saving.

scholarly journals Photonic Integrated Reconfigurable Linear Processors as Neural Network Accelerators

2021 ◽  
Vol 11 (13) ◽  
pp. 6232
Author(s):  
Lorenzo De Marinis ◽  
Marco Cococcioni ◽  
Odile Liboiron-Ladouceur ◽  
Giampiero Contestabile ◽  
Piero Castoldi ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Energy Efficiency ◽  
Silicon Nitride ◽  
Extinction Ratio ◽  
Silicon On Insulator ◽  
Optical Losses ◽  
Linear Transformations ◽  
Feature Maps ◽  
Matrix Vector

Reconfigurable linear optical processors can be used to perform linear transformations and are instrumental in effectively computing matrix–vector multiplications required in each neural network layer. In this paper, we characterize and compare two thermally tuned photonic integrated processors realized in silicon-on-insulator and silicon nitride platforms suited for extracting feature maps in convolutional neural networks. The reduction in bit resolution when crossing the processor is mainly due to optical losses, in the range 2.3–3.3 for the silicon-on-insulator chip and in the range 1.3–2.4 for the silicon nitride chip. However, the lower extinction ratio of Mach–Zehnder elements in the latter platform limits their expressivity (i.e., the capacity to implement any transformation) to 75%, compared to 97% of the former. Finally, the silicon-on-insulator processor outperforms the silicon nitride one in terms of footprint and energy efficiency.

scholarly journals Efficiency of Various Time-Frequency Representations in Deep Neural Network based Passive Sonar Target Classifiers

2020 ◽  
Vol 9 (4) ◽  
pp. 1908-1918
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Target Recognition ◽  
Classification Performance ◽  
Low Frequencies ◽  
Acceptable Error ◽  
Time Frequency ◽  
Passive Sonar ◽  
Spectral Components

Passive acoustic target classification is an exceptionally challenging problem due to the complex phenomena associated with the channel and the relatively low Signal to Noise Ratio (SNR) manifested by the pervasive ambient noise field. Inspired by the overwhelming success of Deep Neural Networks (DNNs) in many such hard problems, a carefully crafted network specifically for target recognition application has been employed in this work. Although deep neural networks can learn characteristic features or representations directly from the raw observations, domain specific intermediate representations can mitigate the computational requirements as well as the sample complexity required to achieve an acceptable error rate in prediction. As the sonar target records are essentially a time series, spectro-temporal representations can make the intricate relationship between time and spectral components more explicit. In a passive sonar target recognition scenario, since most of the defining spectral components reside at the lower part of the spectrum, a nonlinear dilated spectral scale having an emphasis on low frequencies is highly desirable. This can be easily achieved using a filterbank based time-frequency decomposition, which allows more filters to be positioned at the desired frequency ranges of interest. In this work, a rigorous analysis of the performance of time-frequency representations initialized at various frequency scales, is conducted independently as well as in combination. A convolutional neural network based spectro-temporal feature learner has been utilized as the initial layers, while a deep stack of Long Short Term Memories (LSTMs) with residual connections has been used for learning the intricate temporal relationships hidden in the intermediate representations. From the experimental results it can be observed that a linear scale spectrogram achieves an accuracy of 92.4% and 90.2% respectively for validation and test sets in the single feature configuration, whereas the gammatone spectrogram is capable of attaining an accuracy in the order of 96.7% and 96.1% respectively for the same. In a multifeatured setup however, the accuracy reaches up to 97.3% and 96.6% respectively, which reveals that a combination of properly initialized intermediate representations can improve the classification performance significantly.

Sign in / Sign up

Export Citation Format

Share Document