Wyniki wyszukiwania - BazTech

1

Design of urban sludge emission reduction optimisation strategy based on fuzzy neural network

Zhou You-Fei, Hu Wei-Jie, Sheng Jun, Zhou Juan-Juan, Zou Wei-Guo

Ecological Chemistry and Engineering. S

|

2023

|

Vol. 30, nr 2

243--250

EN

Urban sewage sludge treatment is important for sustainable utilisation and virtuous cycle of freshwater resources. However, with the improvement of sewage discharge standards, ensuring stable operation of sewage sludge treatment plants is becoming an urgent problem to be solved in the sewage treatment industry. This paper proposes a FNN control framework based on different working conditions to optimise the whole process of municipal sewage sludge treatment and discharge. The framework first divides the working conditions according to the weather, forming a separate feature and an input vector together with the typical indicators of other sewage treatment plants. Then the FNN is used to complete the control and optimisation of various indicators, achieving the dual objectives of reducing energy consumption and optimising water quality. Finally, the model is tested for the tracking index of sewage flow. The results demonstrate that the FNN control method used has significantly lower MAE than the single method in the two indexes of energy consumption and water quality evaluation. This provides new ideas for the optimisation of urban sewage sludge treatment process in the future. Overall, the paper effectively highlights the importance of urban sewage sludge treatment and presents a well-designed FNN control framework for optimising the treatment process. Additionally, the paper could benefit from further elaboration on the significance of the results obtained, and suggestions for future research in this area.

2

A modified particle swarm optimization procedure for triggering fuzzy flip-flop neural networks

Kowalski Piotr A., Słoczyński Tomasz

International Journal of Applied Mathematics and Computer Science

|

2021

|

Vol. 31, no. 4

577--586

EN

The aim of the presented study is to investigate the application of an optimization algorithm based on swarm intelligence to the configuration of a fuzzy flip-flop neural network. Research on solving this problem consists of the following stages. The first one is to analyze the impact of the basic internal parameters of the neural network and the particle swarm optimization (PSO) algorithm. Subsequently, some modifications to the PSO algorithm are investigated. Approximations of trigonometric functions are then adopted as the main task to be performed by the neural network. As a result of the numerical verification of the problem, a set of rules are developed that can be helpful in constructing a fuzzy flip-flop type neural network. The obtained results of the computations significantly simplify the structure of the neural network in relation to similar conditions known from the literature.

3

Simulation and Analysis of Sintering Furnace Temperature Based on Fuzzy Neural Network Control

Chaoxin Zou, Rong Li, Zhiping Xie, Ming Su, Jingshi Zeng, Xu Ji, Xiaoli Ye, Ye Wang

Archives of Foundry Engineering

|

2021

|

Vol. 21, iss. 1

23--30

EN

Aiming at the problems of delay and couple in the sintering temperature control system of lithium batteries, a fuzzy neural network controller that can solve complex nonlinear temperature control is designed in this paper. The influence of heating voltage, air inlet speed and air inlet volume on the control of temperature of lithium battery sintering is analyzed, and a fuzzy control system by using MATLAB toolbox is established. And on this basis, a fuzzy neural network controller is designed, and then a PID control system and a fuzzy neural network control system are established through SIMULINK. The simulation shows that the response time of the fuzzy neural network control system compared with the PID control system is shortened by 24s, the system stability adjustment time is shortened by 160s, and the maximum overshoot is reduced by 6.1%. The research results show that the fuzzy neural network control system can not only realize the adjustment of lithium battery sintering temperature control faster, but also has strong adaptability, fault tolerance and anti-interference ability.

4

Forecasting return products in an integrated forward/reverse supply chain utilizing an ANFIS

Kumar D. T., Soleimani H., Kannan G.

International Journal of Applied Mathematics and Computer Science

|

2014

|

Vol. 24, no. 3

669--682

EN

Interests in Closed-Loop Supply Chain (CLSC) issues are growing day by day within the academia, companies, and customers. Many papers discuss profitability or cost reduction impacts of remanufacturing, but a very important point is almost missing. Indeed, there is no guarantee about the amounts of return products even if we know a lot about demands of first products. This uncertainty is due to reasons such as companies’ capabilities in collecting End-of-Life (EOL) products, customers’ interests in returning (and current incentives), and other independent collectors. The aim of this paper is to deal with the important gap of the uncertainties of return products. Therefore, we discuss the forecasting method of return products which have their own open-loop supply chain. We develop an integrated two-phase methodology to cope with the closed-loop supply chain design and planning problem. In the first phase, an Adaptive Network Based Fuzzy Inference System (ANFIS) is presented to handle the uncertainties of the amounts of return product and to determine the forecasted return rates. In the second phase, and based on the results of the first one, the proposed multi-echelon, multi-product, multi-period, closed-loop supply chain network is optimized. The second-phase optimization is undertaken based on using general exact solvers in order to achieve the global optimum. Finally, the performance of the proposed forecasting method is evaluated in 25 periods using a numerical example, which contains a pattern in the returning of products. The results reveal acceptable performance of the proposed two-phase optimization method. Based on them, such forecasting approaches can be applied to real-case CLSC problems in order to achieve more reliable design and planning of the network.

5

Fuzzy control based on "true and false" philosophy for mechatronics systems

Tran C.

Computer Assisted Mechanics and Engineering Sciences

|

2009

|

Vol. 16, No. 1

11-20

EN

For man, possessing the ability to recognize the specific situation that has arisen at any instant of time and taking the appropriate decision without using a mathematical model is what 'adaptation' means. Adaptive principles are being extended to more complex systems in widely different areas, in which we need to replace the traditional metaphor of a fixed environment with a dynamic and constantly changing one. Each mechatronic system, for example, is usually, faced with a multiplicity of choices and objectives of the system change with it. Its modeling reąuires more than a mathematical model that is based on clear definitions and axioms using the rules of logic deduction theory. To solve this problem, the new concept of system integration by software control, such as real-time multi-tasking operating system using fuzzy logic, is emphasized in the education of modem mechatronics engineering. In this paper, I would like to return, firstly, to the fundamental element of truth measure, which we can use as basis for constructing a way to spread the binary philosophy rather than its rejecting and to increase our ability to describe the real world. Next, in order to explanation into details one aspect of real-time software using fuzzy logic, applied in control of mechatronic systems, we present a fuzzy control technology that combines artificial intelligence and control methodologies. It achieves control purposes based on expert knowledge and experience expressed in the form of IF-THEN rules (Sugeno-type) or neural networks using neuro-fuzzy based intelligent control scheme in order to create a real-time-adaptive control process. Application of this technology is presented in numerical example of trajectory control of PUMA 560 robot manipulators using Fuzzy Artificial Neural Network, FANN, rather than using Artificial Neural Network, ANN, only.

6

Determination of the shear speed of soil triaxial testing based on fuzzy logic

Tran C.

Computer Assisted Mechanics and Engineering Sciences

|

2008

|

Vol. 15, No. 2

113-121

EN

To design foundations, embankments and other soil structures, geotechnical engineers require methods of assessing engineering properties of soils. Some of the more complex phenomena that occur in soils have often been difficult to recreate in a laboratory: seismic activity, vibration, unsaturated condition, control of principal stresses etc. are areas which have proven difficult to replicate, despite their importance of being understood. This was partly due to the lack of test systems capable of reproducing these effects and the complexity of test systems that were developed to carry out such work. A number of advanced computer/software controlled systems allow the geotechnical engineer to perform the most complex test regimes via a user-friendly software interface. However, it is difficult to determine firstly parameters needed, e.g. shear speed in soil triaxial testing. In this paper we represent a new approach to determine this shear speed by solving the inverse problem using testing results obtained by the forward procedure. Direct search method, i.e. Adaptive Neuro-Fuzzy Inference System (ANFIS), is developed and applied to soil triaxial shear tests. It allows us to use the advanced sensor and actuator technologies in order to change the traditional triaxial shear apparatus from a mechanical system to a mechatronics system in next work.

7

Extraction of fuzzy rules using deterministic annealing integrated with ε-insensitive learning

Czabański R.

International Journal of Applied Mathematics and Computer Science

|

2006

|

Vol. 16, no 3

357-372

EN

A new method of parameter estimation for an artificial neural network inference system based on a logical interpretation of fuzzy if-then rules (ANBLIR) is presented. The novelty of the learning algorithm consists in the application of a deterministic annealing method integrated with ε-insensitive learning. In order to decrease the computational burden of the learning procedure, a deterministic annealing method with a “freezing” phase and ε-insensitive learning by solving a system of linear inequalities are applied. This method yields an improved neuro-fuzzy modeling quality in the sense of an increase in the generalization ability and robustness to outliers. To show the advantages of the proposed algorithm, two examples of its application concerning benchmark problems of identification and prediction are considered.

8

Application of fuzzy neural network for supporting measurements and control in a wastewater treatment plant

Skowroński Z. G., Skowrońska K. T., Biziuk M. K.

Chemia Analityczna

|

2006

|

Vol. 51, No. 3

351-363

EN

Wastewater treatment has become a very important aspect of environmental protection. The main goal of a wastewater treatment plant (WWTP) is to reduce the level of waste-water pollution. The application of AT (artificial intelligence) techniques in wastewater treatment provides an alternative way of operating complex process, helps to reduce energy consumption and to improve the efficiency of the equipment. Modern control systems developed in the recent years are often based on complex mathematical models of the processes, which allow one to develop an optimized treatment strategy. However, they require the knowledge of several parameters that are not commonly measured in a WWTP or they are not measured with often enough for control purposes. One of them is COD (chemical oxygen demand). The procedure of its measurement is long and thus problematic. !n this work we have proposed a new approach to the COD control system and its further improvement applying FNN (fuzzy neural network). The main goal was to shorten and simplify determination of COD based on the on-line parameter. The developed approach is expected to be successfully applicable in the real time system control.

PL

Oczyszczanie ścieków jest jednym z ważniejszych aspektów ochrony środowiska. Nowoczesne systemy kontroli w oczyszczalniach ścieków pozwalają na poprawę jakości procesu oczyszczania redukując jednocześnie koszty. Systemy kontroli i optymalizacji, jakie od kilku lat opracowuje się dla oczyszczalni ścieków, bazujązazwyczaj na skomplikowanych modelach matematycznych. Kluczowym problemem w zastosowaniu tych systemów jest duża liczba parametrów, które nie są zazwyczaj mierzone lub częstotliwość pomiarówjest nicwystarczającaz punktu widzenia systemów kontroli. ChZT (chemiczne zapotrzebowanie na tlen) jest jednym z takich parametrów. Odgrywa on kluczową rolę w modelowaniu procesów osadu czynnego, jednakże, ze względu na długi czas analizy, jego zastosowanie w układzie kontroli jest utrudnione. W tej pracy określono sposoby s/ybkiego wyznaczania przybliżonej wartości ChZT na podstawie innych parametrów z zastosowaniem rozmytych sieci neuronowych.

9

Application of a fuzzy neural network for river water quality prediction

Skowrońska K. T., Skowroński Z. G., Biziuk M. K.

Chemia Analityczna

|

2006

|

Vol. 51, No. 3

365-375

EN

Monitoring and modelling of river water quality is one of the key elements in the global environmental monitoring policy and management. The control of complex and nonlinear systems, like rivers, is not an easy task. Usually, mathematical models are used for this purpose; however, sometimes these models require so much data that the response time is too long. An application of artificial intelligence (AI) helps to avoid disadvantages of mathematical models. This paper presents an application of the fuzzy neural network to the prediction of river water quality parameters. As an example, Cu concentration has been predicted.

PL

Monitoring i modelowanie zmian w jakości wód powierzchniowych stanowią jeden z kluczowych elementów monitoringu i zarządzania ochroną środowiska na skale globalną. Kontrolowanie tak złożonych i nieliniowych w swojej charakterystyce obiektów, jakimi są rzeki, jest trudnym zadaniem. Zazwyczaj do tego celu wykorzystuje się modele matematyczne, jednak czasem wymagają one bardzo dużej ilości danych lub czas oczekiwania na odpowiedź (uzyskania danych wyjściowych) jest zbyt długi. Zastosowanie technik sztucznej inteligencji pomaga uniknąć części wad modeli matematycznych. Ta praca przedstawia zastosowanie rozmytych sieci neuronowych do przewidywania parametrów charakteryzujących jakość wody rzecznej na przykładzie przewidywania stężenia miedzi.

10

An Expert System Coupled With a Hierarchical Structure of Fuzzy Neural Networks for Fault Diagnosis

Calado J. M. F., Costa I. S.

International Journal of Applied Mathematics and Computer Science

|

1999

|

Vol. 9, no 3

667-687

EN

An on-line fault diagnosis system, designed to be robust to the normal transient behaviour of the process, is described. The overall system consists of an expert system cascade with a hierarchical structure of fuzzy neural networks, corresponding to a multi-stage fault detection and isolation system. The fault detection is performed through the expert system by means of fault detection heuristic rules, generated from deep and shallow knowledge of the process under consideration. If a fault is detected, the hierarchical structure of fuzzy neural networks starts and it performs the fault isolation task. The structure of this diagnosis system was designed to allow for the diagnosis of single and multiple simultaneous abrupt and incipient faults from only single abrupt fault symptoms. Also, it combines the advantages of both fuzzy reasoning and neural networks learning capacity. A continuous binary distillation column has been used as a test bed of the current approach. Single, double and triple simultaneous abrupt faults, as well as incipient faults, have been considered. The preliminary results obtained show a good accuracy, even in the case of multiple faults.

11

A fuzzy neural network for knowledge acquisition in complex time series

Kasabov N., Kim J., Kozma R.

Control and Cybernetics

|

1998

|

Vol. 27, no 4

593-611

EN

A novel fuzzy neural network, called FuNN, is applied here for time-series modeling. FuNN models have several features that make them well suited to a wide range of knowledge engineering applications. These strengths include fast and accurate learning, good generalisation capabilities, excellent explanation facilities in the form of semantically meaningful fuzzy rules, and the ability to accomodate both numerical data and existing expert knowledge about the problem under consideration. We investigate the effectiveness of the proposed neuro-fuzzy hybrid architectures for manipulating the future behaviour of nonlinear dynamical systems and interpreting fuzzy if-then rules. A well-known example of Box and Jenkins is used as a benchmark time series in the proposed modelling approach and the other modelling approach. Finally, experimental results and comparisons with the other popular neuro-fuzzy inference system, namely Adaptive Network-based Fuzzy Inference System (ANFIS) are also presented.