Wyniki wyszukiwania - BazTech

1

Smart district heating networks in the era of energy transformation

Wrzalik Aleksandra

System Safety : Human - Technical Facility - Environment

|

2022

|

Vol. 4, nr 1

58-66

EN

District heating, which accounts for half of the EU's energy consumption, still relies heavily on fossil fuels. This causes emissions of dust and greenhouse gases and into the atmosphere and leads to negative climate changes. For this reason, European Union countries have been implementing a climate and energy policy for many years, which in the area of heating is aimed at making it more efficient and sustainable. This requires the introduction of low-carbon technologies and the reduction of fossil fuel consumption by increasing the share of renewable energy sources. Modern, efficient and smart heating systems should guarantee reliable heat supply while reducing the environmental impact. The article discusses the direction of change and development of district heating systems through the introduction of innovative technologies. The new generations of 4GDH and 5 GDH district heating systems are described and the benefits of their use are indicated. The concept of smart district heating networks, their structure and the advantages of their implementation are discussed. The possibilities of creating smart energy systems using renewable energy sources and heat storage technologies were also indicated. The activities of Polish district heating companies in the introduction of smart heat networks are presented, based on research conducted.

2

Intelligent enterprise capital control based on Markov chain

Andriushchenko Kateryna, Liezina Anastasiia, Lavruk Vitalii, Sliusareva Liudmyla, Rudevska Viktoriia

Acta Innovations

|

2022

|

no. 45

18--30

EN

This scientific work is devoted to the processes of creating technologies, as well as the use of their mathematical representation in the form of models in the context of the formation and development of the intellectual capital of an enterprise. To select a goal, a vision was formed to prove or refute any possibility of using Markov's theory in practice, namely the creation of a stochastic model of the intellectual capital of an enterprise in monetary terms, which manifests itself in investments in intangible assets. As an initial model hypothesis, the statement is accepted that investments in the enterprise's intangible assets are a factor in the transformation of intellectual capital into the company's value. Based on the results of applying the stochastic Markov chain model, the potential profit of the company's intangible assets was estimated, the main elements of which were intellectual capital assets during the study. A matrix of transition probabilities has been formed and modeling of the limiting probabilities of the system states has been implemented. The necessary conditions and boundaries of the scope of the mathematical model are also determined. The mathematical method of modeling the company's intellectual capital proposed in the article allows determining the contribution of each of the structural components to the formation of the value of the enterprises intellectual capital, thereby making it possible to establish a current balance between all its elements, which contributes to a comprehensive study of the company's intellectual assets.

3

Self-improving Q-learning based controller for a class of dynamical processes

Musial Jakub, Stebel Krzysztof, Czeczot Jacek

Archives of Control Sciences

|

2021

|

Vol. 31, No. 3

527--551

EN

This paper presents how Q-learning algorithm can be applied as a general-purpose self-improving controller for use in industrial automation as a substitute for conventional PI controller implemented without proper tuning. Traditional Q-learning approach is redefined to better fit the applications in practical control loops, including new definition of the goal state by the closed loop reference trajectory and discretization of state space and accessible actions (manipulating variables). Properties of Q-learning algorithm are investigated in terms of practical applicability with a special emphasis on initializing of Q-matrix based only on preliminary PI tunings to ensure bumpless switching between existing controller and replacing Q-learning algorithm. A general approach for design of Q-matrix and learning policy is suggested and the concept is systematically validated by simulation in the application to control two examples of processes exhibiting first order dynamics and oscillatory second order dynamics. Results show that online learning using interaction with controlled process is possible and it ensures significant improvement in control performance compared to arbitrarily tuned PI controller.

4

A hybrid system with intelligent control for the processes of resource and energy supply of a greenhouse complex with application of energy renewable source

Syrotiuk Valerii, Syrotyuk Serhiy, Ptashnyk Vadym, Тryhuba Аnatoliy, Baranovych Serhii, Giełżecki Jan, Jakubowsk Tomasz

Przegląd Elektrotechniczny

|

2020

|

R. 96, nr 7

149--152

EN

The algorithm of control for the regime of artificial supplementary lighting of plants can secure the light regime, according to their kind and phase of vegetation growth. A peculiarity of the proposed algorithm suggests use of the information about a short-term weather forecast, which supplies the maximum employment of solar radiation energy in the technological process of artificial lighting of plants.

PL

Algorytm sterowania dla systemu sztucznego doświetlania roślin można zastosować w systemie oświetlenia, w zależności od fazy wzrostu roślinności i ich rodzaju. Specyfika proponowanego algorytmu sugeruje wykorzystanie informacji o krótkoterminowej prognozie pogody, która zapewnia maksymalne wykorzystanie energii promieniowania słonecznego w procesie technologicznym sztucznego oświetlenia roślin. System hybrydowy z inteligentnym sterowaniem procesami zaopatrzenia w energię kompleksu szklarniowego z zastosowaniem odnawialnych źródeł energii.

5

Novel Fuzzy-Based Self-Adaptive Single Neuron PID Load Frequency Controller for Power System

Eissa M. Abdullah

Power Electronics and Drives

|

2019

|

Vol. 4 (39)

141--150

EN

This paper proposes a newly adaptive single-neuron proportional integral derivative (SNPID) controller that uses fuzzy logic as an adaptive system. The main problem of the classical controller is lacking the required robustness against disturbers, measurement noise in industrial applications. The new formula of the proposed controller helps in fixing this problem based on the fuzzy logic technique. In addition, the genetic algorithm (GA) is used to optimize parameters of the SNPID controller. Because of the high demands on the availability and efficiency of electrical power production, the design of robust load-frequency controller is becoming increasingly important due to its potential in increasing the reliability, maintainability and safety of power systems. So, the proposed controller has been applied for load-frequency control (LFC) of a single-area power system. The effectiveness of the proposed SNPID controller has been compared with the conventional controllers. The simulation results show that the proposed controller approach provides better damping of oscillations with a smaller settling time. This confirms its superiority against its counterparts. In addition, the results show the robustness of the proposed controller against the parametric variation of the system.

6

Design and development of an intelligent biomechatronic tumor prosthesis

Kocaoglu Sitki, Akdogan Erhan

Biocybernetics and Biomedical Engineering

|

2019

|

Vol. 39, no. 2

561--570

EN

Nowadays, bone cancer patients using expandable prostheses (EPs) have to go to the clinic frequently to determine the limb length and to perform the extension if necessary, as long as their age-based growth lasts. This situation brings along problems such as increased physician workload, the patient's exposure to radiation at each measurement, a larger rate of extension due to the long interval period between each extension and thus reducing patient comfort as well as making the daily life of the patient difficult. In this study, a biomechatronic tumor prosthesis which is able to determine the need for extension by means of its hardware and intelligent control structure was developed to eliminate the aforementioned problems. Mechanical analysis of the designed prosthesis has been performed in the simulation environment, the prototype of the prosthesis has been produced, wireless communication and control system have been created and the performance of the system has been tested on the experimental setup. Limb length discrepancies (LLDs) of 1 mm and above between the healthy limb and the limb with a prosthesis were able to be detected by the system, and prosthesis extension procedure was successfully performed against the maximum soft tissue resistance to be possibly encountered.

7

Intelligent control of CO2-EOR process

Mikołajczak E., Stopa J., Wojnarowski P., Janiga D., Czarnota R.

AGH Drilling, Oil, Gas

|

2018

|

Vol. 35, no. 1

235--243

EN

One of the enhanced oil recovery methods, which enables to recover an additional 15–20% of oil resources is the CO2-EOR method based on carbon dioxide injection into partially depleted reservoirs. Determination of the optimal process control facilitates effective use of natural resources. The idea of this paper is to develop an algorithm that optimizes the CO2-EOR process. This algorithm is based on the combination of artificial intelligence, control theory and computer simulation of hydrocarbon reservoirs. The effect of the proposed solution is the CO2-EOR process control, which is optimal in the case of the adopted objective function expressing the economic value of the project. The obtained results suggest that the use of artificial intelligence methods in the hydrocarbon production allows to improve the process efficiency by an additional 31% compared to the project carried out with the use of engineering knowledge.

8

Safety and intelligent control system for plasmatron application

Szałatkiewicz J.

Journal of KONES

|

2017

|

Vol. 24, No. 2

247--252

EN

This article presents safety and intelligent control systems essential for safe and reliable operation of DC arc plasmatron. Presented methods and techniques are also applicable to other types of plasmatrons and devices. Author presents and describes subsystems of DC arc plasmatrons including its: start up and operation algorithms, detection of malfunction’s, control parameters and techniques for plasmatron operation. Moreover, issues and requirements identified in field operation are presented in case of plasmatron operation on site, communication and supervisory system for flexible integration of independent device in complex SCADA systems. Presented material covers also safety techniques, procedures and subsystems necessary for safe and reliable plasmatron operation, with examples of experience in plasmatrons applications. Presented in this article plasmatrons control and safety systems with theirs functions together with operation algorithms were applied and validated in constructed and operated plasmatrons. Plasmatrons were tested in different environments. For example in the plasmatron plasma reactor where three 20 kW plasmatrons were used and installed directly in high temperature refractory that consisted of plasma incineration and smelting of metals chamber.

9

Collaborative intelligence - definition and measured impacts on internetworked e-work

Zhong H., Levalle R. R., Moghaddam M., Nof S. Y.

Management and Production Engineering Review

|

2015

|

Vol. 6, No. 1

67--78

EN

Internetworked e-Work is enabling new channels in cyber space for collaboration among physical and cyber agents, e.g., humans, robots, software agents. Research on Collaborative Control Theory (CCT) indicates that building and augmenting the Collaborative Intelligence (CI) of participants in cyber-physical networks can provide better support for achieving their individual and common goals. In spite of its rising significance and popularity, however, no clear and precise definition and universal quantitative measure has been proposed for the CI. In this article, we first formalize the CI by suggesting a formal definition, based on the definitions of its elements - collaboration and intelligence. We then propose a quantitative measure for the CI, adapted from the universal intelligence measure. For illustration, we analyze three recent collaborative e-Work studies at three different scales: (1) Telerobotenabled computer supported collaborative design; (2) Collaborative product line control in supply networks; (3) Demand and capacity sharing in multi-enterprise collaboration. From these case studies, common advantages such as work efficiency, network robustness and stability, service level, resource utilization, and collaboration cost are observed, analyzed, and translated into formal CI measures. Results indicate significant impacts of CI on the efficiency, effectiveness, and quality of collaborative activities in emerging e-Work networks.

10

Innowacje w oświetleniu drogowym

Kuczyński K.

Elektro Info

|

2014

|

nr 10

76--77

11

Intelligent electronic embedded systems for the protection of railway transport from accidents

Potapovs A., Gorobetz M., Levchenkov A.

Archives of Transport System Telematics

|

2011

|

Vol. 4, iss. 3

24-30

EN

The paper considers an intelligent electronic embedded system for the protection of railway transport from accidents, its compatibility with the existing railway control system, principles of its components interoperation and control algorithms. The paper gives the definitions of the functions performed by the system considered and its mathematical description applied to the realization of the control algorithm. The process of the device prototype testing is described with the obtained results, advantages and further prospects

12

Intelligent PI controller and its application to dissolved oxygen tracking problem

Zubowicz T., Brdys M. A., Piotrowski R.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2010

|

Vol. 4, No. 3

16-24

EN

The paper addresses design, calibration, implementation and simulation of the intelligent PI controller used for dissolved oxygen (DO) tracking at wastewater treatment plant (WWTP). The calibration process presented in this paper utilizes both engineering and scientific methods. Verification of the control system design method was obtained via simulation experiments.

13

The HeKatE methodology. Hybrid engineering of intelligent systems

Nalepa G. J., Ligęza A.

International Journal of Applied Mathematics and Computer Science

|

2010

|

Vol. 20, no 1

35-53

EN

This paper describes a new approach, the HeKatE methodology, to the design and development of complex rule-based systems for control and decision support. The main paradigm for rule representation, namely, eXtended Tabular Trees (XTT), ensures high density and transparency of visual knowledge representation. Contrary to traditional, flat rule-based systems, the XTT approach is focused on groups of similar rules rather than on single rules. Such groups form decision tables which are connected into a network for inference. Efficient inference is assured as only the rules necessary for achieving the goal, identified by the context of inference and partial order among tables, are fired. In the paper a new version of the language-XTT2-is presented. It is based on ALSV(FD) logic, also described in the paper. Another distinctive feature of the presented approach is a top-down design methodology based on successive refinement of the project. It starts with Attribute Relationship Diagram (ARD) development. Such a diagram represents relationships between system variables. Based on the ARD scheme, XTT tables and links between them are generated. The tables are filled with expert-provided constraints on values of the attributes. The code for rule representation is generated in a humanreadable representation called HMR and interpreted with a provided inference engine called HeaRT. A set of software tools supporting the visual design and development stages is described in brief.

14

Inteligentne sterowanie ogrzewaniem podłogowym

Walczak T.

Fizyka Budowli w Teorii i Praktyce

|

2010

|

T. 5, nr 2

51-54

PL

W pracy przedstawiono wyniki eksperymentów numerycznych związanych z aktywnym wykorzystaniem masy termicznej budynku jako magazynu energii cieplnej, pochodzącej z tańszej taryfy nocnej. Element grzejny umieszczono w masywnej podłodze a do jego sterowania wykorzystano zaawansowane techniki sztucznej inteligencji. Uzyskano kilkuprocentowe obniżenie kosztów ogrzewania w stosunku do obecnie stosowanych systemów sterowania.

EN

The results of the investigation of energy performance of massive building envelope with a heating element placed in the massive floor has been shown in the paper. The proposed control approach of floor heating system is based on the advanced artificial intelligent methods. The results show that the floor heating system has good thermal storage performance, which can be used to a night-running model to obtain energy-saving benefits efficient and economic running cost. Investigated algorithm shows a few percent potential to decrease energy cost, in comparison to typical used control systems.

15

Interaction of real and embedded devices for intelligent control of city electric transport

Potapovs A., Gorobetz M., Levchenkov A.

Archives of Transport System Telematics

|

2010

|

Vol. 3, iss. 4

37-41

EN

The interaction of real and virtual devices is an important point in the design and development of control system. The central part of an embedded control system is a controller and it needs input devices and output sensors for realization of the control. The proposed approach allows using a real controller with its specific programming tools and languages for intelligent software development and virtual measurement and sensor devices realized in a computer environment. Different wireless compounds are necessary for intelligent embedded devices for transport system control. For this reason a wireless communication network is needed to ensure the data transmission between the controller and supervisory control and data acquisition system. The purpose of this paper is to propose an approach for interaction of real, embedded and virtual devices in electric transport control systems. The main tasks are: to analyze objects and functional dependencies of an electric transportation control system, to develop a control algorithm with the interaction of real and virtual devices, to ensure a wireless connection for the data transfer from the controller to the supervisory control and data acquisition system, to define the method of transmitted data processing. Computer and practical experiments, with real and embedded devices, and the results analysis will be described the paper.

16

The HMI/SCADA in control systems and supervision processes of manufacturing transport

Smoczek S., Sznytko J.

Journal of KONES

|

2008

|

Vol. 15, No. 3

499-507

EN

The aim of the paper is integrated control and supervisory systems of works transport process, which were realized using programming application type of HMI/SCADA (Human Machine Interface/Supervisory Control and Data Acquisition). The grater requirements put before automation and HMI/SCADA systems in range of controlling and supervising industrial processes cause that is more and more expected evolution of such system to integrate solutions and tools which allow realizing compound tasks connected with control, diagnostic, monitoring and managing. From supervisory systems are expected solutions, which enable to aid decision-making processes for making faster and adequate diagnosis of occurrences and failures, proper estimating technical states of devices, formulating conclusions about symptoms-failures relationships and preventive or removing actions. It needs to develop tools using intelligent methods and algorithms based on fuzzy logic, experts systems and artificial neural networks, which can be applied to realize inference systems to help decision-making processes, control and diagnostic tasks. Presented in the paper examples of HMI/SCADA systems consider realization of controlling and supervising tasks with the aid of fuzzy logic and heuristic algorithms. Supervisory system of works transport process shown in the paper was based on heuristic base of knowledge used to aid decision-making process of operator.

17

System integration of a multivariable process plant utilising an intelligent control technique

Naidoo P., Govender D. T. P., van Niekerk T. I.

Journal of Achievements in Materials and Manufacturing Engineering

|

2008

|

Vol. 31, nr 2

540-546

EN

Purpose: The research objective is to maintain a desired process outlet temperature. Firstly, communication between the control system and the process field devices by means of Profibus-PA and Profibus-DP is established. Secondly the process flow rate and level in the supply vessel must be controlled in the same system. The final manipulated variable, an air-to-open control valve is regulated to achieve the research objective [2]. The paper will discuss introductory aspects of Profibus and simulated results on the knowledge based controller as the research is on-going. Design/methodology/approach: The research project comprises the design, engineering and analysis of a multi input/output rule-based process control system on the Profibus communication platform. A programmable logic controller is configured to control the plant and a Profibus system is used to communicate input and output signals between the field instrumentation and the process control system. Findings: The plant and control knowledge derived for the design of the decision-making control algorithm in the research was obtained from available data in the open-loop mode as the plant is still to be commissioned. The designed algorithm will be tested on the process plant in comparison with the simulated results in order to evaluate its feasibility in a networked control system for temperature, level and flow on a Profibus-DP and Profibus-PA network. A mathematically-based control strategy will contribute to increasing the settling time tremendously thereby impacting negatively on factors like production time and quality. Practical implications: The process control system will monitor and control measured variables such as flow, temperature and level on a typical industrial plant. The plant will be used to transfer technology education and training to industry and practitioners alike. Originality/value: The control strategy emerging from this research may be applied to similar process plants in industry.

18

Emotional learning based intelligent speed and position control applied to neurofuzzy model of switched reluctance motor

Rouhani H., Sadeghzadeh A., Lucas C., Araabi B. N.

Control and Cybernetics

|

2007

|

Vol. 36, no 1

75-95

EN

In this paper, rotor speed and position of a Switched Reluctance Motor (SRM) are controlled using an intelligent control algorithm. The controller is working based on a PID signal while its gain is permanently tuned by means of an Emotional Learning Algorithm to achieve a better control performance. Here, nonlinear characteristic of SRM is identified using an efficient training algorithm (LoLiMoT) for Locally Linear Neurofuzzy Model as an unspecified nonlinear plant model. Then, the Brain Emotional Learning Based Intelligent Controller (BELBIC) is applied to the obtained model. While the intelligent controller works based on a computational model of a limbic system in the mammalian brain, its contribution is to improve the performance of a classic controller like PID without much more control effort. The results demonstrate excellent improvements of control action in different working situations.

19

SIMOCODE pro oraz sterowniki SIMATIC w praktyce - w zakładach chemicznych w Inowrocławiu

Frankowski G., Janiszewski R., Kuczma S.

Napędy i Sterowanie

|

2006

|

R. 8, nr 7/8

18-24

PL

Inowrocławskie Zakłady Chemiczne SODA MĄTWY z Grupy Kapitałowej CIECH SA są jednym z dwóch w Polsce producentów sody oraz produktów sodopochodnych. Firma funkcjonuje od prawie 130 lat. Stary zakład - wybudowany w 2. połowie XIX wieku - został zlikwidowany w latach 1995-2000. Obecnie trzon przedsiębiorstwa stanowi wytwórnia sody wybudowana przed ok. 30 laty i rozbudowywana oraz modernizowana do chwili obecnej. Ważną rolę odgrywają przy tym moduły inteligentnego sterowania układów napędowych - SIMOCODE - oraz nowoczesne systemy sterowania oparte o sterowniki SIMATIC.

20

Intelligent control of the electric - arc steelmaking process using artificial neural networks

Wieczorek T.

Computer Methods in Materials Science

|

2006

|

Vol. 6, No. 1

9-14

EN

Development of computational intelligence allows to combine some conventional approaches with artificial intelligence modules, like Artificial Neural Networks (ANNs). The combination leads to so-called Intelligent Systems which potential is practically unlimited. ANNs based models for electrodes positioning, prediction of the electric energy consumption and end-of-heat in electric arc furnaces were implemented by number of authors and they have obtained applicable practical results. The present paper describes methods of intelligent control of the EAF steelmaking process, particularly neural control. The elaborated neural network models for smelting control in the EAF are discussed. The goal is to provide a compact review of neural modeling and control methods and their capabilities for the EAF steelmaking process.

PL

Rozwój metod tzw. inteligencji obliczeniowej pozwała na łączenie tradycyjnego modelowania z modułami sztucznej in ligencji, jak np. Sztuczne Sieci Neuronowe (SSN). Prowadzi do budowy tzw. Inteligentnych Systemów Informatycznych,których możliwości są praktycznie nieograniczone. Oparte na SSN modele pozycjonowania elektrod pieca, przewidywanie zużycia energii elektrycznej i czasu końca wytopu w elektrycznych piecach łukowych, zostały wykorzystane przez wielu autorów w konkretnych, praktycznych zastosowaniach. W pracach opisano metody inteligentnego sterowania procesem wytwarzania stali w piecach hakowych, w szczególności metody neuro nowe. Przedyskutowano neuronowy model sterowania roztapia niem wsadu w piecu. Celem pracy jest przeprowadzenie przeglądu metod modelowania i sterowania neuronowego i możliwości ich wykorzystania w badanym procesie stalowniczym.