Home  ›  Chemical Engineering Process Optimization and Control Methods Literature Review

Chemical Engineering Process Optimization and Control Methods Literature Review

Written By ۱۴۰۱ فروردین ۲۸, یکشنبه Add Comment Edit

Open admission peer-reviewed chapter

Application of AI in Chemical Applied science

Submitted: November 22nd, 2017 Reviewed: February 27th, 2018 Published: June 27th, 2018

DOI: ten.5772/intechopen.76027

IntechOpen

IntechOpen Downloads

2,069

Total Affiliate Downloads on intechopen.com

Abstract

A major shortcoming of traditional strategies is the fact that solving chemical engineering problems due to the highly nonlinear behavior of chemical processes is frequently incommunicable or very hard. Today, artificial intelligence (AI) techniques are becoming useful due to simple implementation, piece of cake designing, generality, robustness and flexibility. The AI includes diverse branches, namely, artificial neural network, fuzzy logic, genetic algorithm, expert systems and hybrid systems. They have been widely used in diverse applications of the chemical engineering field including modeling, process control, classification, fault detection and diagnosis. In this affiliate, the capabilities of AI are investigated in diverse chemical applied science fields.

Keywords

  • chemic engineering science
  • AI algorithms
  • classification
  • process control
  • modeling
  • optimization
  • mistake detection and diagnosis

i. Introduction

Bogus intelligence (AI) applications in chemical engineering have increased dramatically recently. This chapter deals with diverse applications of artificial intelligence (AI) in the chemic engineering field including procedure such every bit modeling, optimization, process command, fault detection and diagnosis. The aim of the affiliate is to provide an overview of the field by presenting the capabilities and limitations of using the AI approach, focusing on artificial neural network (ANN) and fuzzy logic methods.

It is shown that complexities of conventional approaches when dealing with chemic processes which are inherently highly nonlinear can exist tackled through the application of AI methods. Four illustrative relevant examples are also presented.

After reading this chapter, the reader is expected to take a basic grounding in the application of AI methods in chemical engineering and sympathize their implementation issues.

Advertisement

2. Awarding of AI in chemical process modeling

Chemical process models which present the organization behavior are useful in all phases of chemic technology, from inquiry and blueprint to optimization and command and fifty-fifty plant operations [1].

Generally, There are two major types of modeling approaches in chemic engineering, namely, mechanistic (white box, kickoff principle) and AI-based arroyo similar ANN and fuzzy logic methods. In the mechanistic approach, cardinal concrete and chemic laws, such as conservation laws, construct the basis of the model. This arroyo contains algebraic and differential equations which involve mass, energy and momentum balances. Due to the large number of variables affecting the process behavior and complex mathematical equations governing the system, many chemical processes are nonlinear and complicated. Consequently, it is hard and sometimes even incommunicable to nowadays them by mechanistic models. Even if such a model has been developed, it might be impractical to solve or identify its parameters. Moreover, a mechanistic model needs detailed knowledge and a lot of skill and ingenuity to incorporate the bones phenomena of the procedure in the model. Difficulties can arise from poor knowledge [2]. In some cases, considering some assumptions such as physical properties' continuance, ideality of gas phase and linearization of the nonlinear equations of the model is inevitable, which all impose limitations on the model leading to the reduction of the model'south robustness [iii].

On the opposite, AI-based techniques take demonstrated their superb ability and take received much attention for chemic procedure modeling. These techniques, for which developing detailed knowledge of the procedure is of less concern, may overcome the drawbacks of the mechanistic approach when dealing with complex and nonlinear systems. Using AI-based methods, inherently qualitative variables in chemical processes similar catalyst deactivation in reactors can also be considered in the model, while these types of variables are non possible to implement in mechanistic models.

The almost common methods of AI for modeling purposes in chemic engineering are ANN and fuzzy logic, which sometimes are hybridized with evolutionary algorithms [four, 5, 6, 7]. In addition to ANN and fuzzy logic methods, their hybrid scheme named adaptive-network-based fuzzy inference arrangement (ANFIS) which is actually a fuzzy inference system implemented in the framework of adaptive networks has as well been applied for modeling purposes in chemic engineering.

The first footstep of developing an AI-based model is defining the input/output variables of the system which is to be modeled (Figure one). Afterward, co-ordinate to the experimental data or the noesis of the governing phenomena, the model is developed. The parameters that narrate the AI-based model like the number of fuzzy sets (when using fuzzy logic), the number and the transfer functions of hidden layers (when using the ANN method) depend on the complication and nonlinearity of the arrangement and the types of variables affecting the procedure.

Figure one.

Schematic of AI model.

Among the types of ANN structures, the multi-layer perceptron (MLP) neural network which has a feed-forward scheme is believed as the most useful topology for organisation modeling [8]. Moreover, the recurrent ANN model which is a mapping of by inputs and outputs to the time to come outputs can be used for dynamic processes.

In the fuzzy model arroyo where the ii types of which are Mamdani [nine] and Takagi-Sugeno (TS) [ten], all the uncertainties and model complications are treated in linguistic expressions in the form of "If-Then" rules based on the theory of fuzzy logic [11]. TS like ANN is ordinarily considered as a data-driven AI-based modeling approach [12].

Mamdani Fuzzy that differs in the manner the information and rules are presented has several superiorities over the TS approach for the modeling of chemic processes. Starting time, qualitative experience and knowledge of the experts who are dealing with the process are incorporated in the development of the model [12]. In addition, there is no need for data in order to build the Mamdani fuzzy model. Consequently, a Mamdani fuzzy model is more intuitive, transparent and interpretable [13]. In contrast, each TS-blazon model is a local approximator and the predictability of the model is valid for the specific operating condition of the process under which the model was developed and tested [xiv]. Appropriately, it tin can hardly be applied for analyzing the process beliefs and cannot be scaled up or down and therefore is less useful for industrial practice. Despite the capabilities of Mamdani method, it is worth underlying that a Mamdani fuzzy model suffers from the large number of rules when dealing with the processes with large number of variables.

Genetic algorithm (GA) tin can exist used to optimize the performance of a fuzzy model. The role of GA is recognized as optimal parameters' estimation such as the parameters of scaling functions and the universes of discourse [fifteen, 16] or the membership functions (MFs) [17, eighteen]. GA is as well applied every bit a method for rule reduction/option by removing some rules similar redundant, unnecessary or misleading ones [17] when dealing with high-dimensional problems in which the number of rules is and so big that it cannot be managed efficiently.

The hybrid Mamdani fuzzy and GA modeling methods normally consist of two principal steps: (i) constructing a kickoff-up version of the model using only the heuristic knowledge and (ii) tuning procedure using the GA. The schematic of this algorithm is shown in Figure 2. In the first step, the output variables determining the behavior of the organization are defined, given that, the input variables which affect the selected output variables are determined. Afterward, a base fuzzy model is divers, characterized past the number and types of fuzzy sets of variables and the production rules presenting the beliefs of the process based on the noesis and expertise of the experts who accept been working with the organization. This model is used as the starting time-up version of the model which has to be tuned. In the second step, GA is formulated for optimization of parameters that characterize model, such as membership function parameters, membership function types and then on.

Figure 2.

Schematic of hybrid Mamdani fuzzy and GA modeling method.

Advertisement

3. Application of AI in optimization of chemical processes

Chemical process optimization has its origins in linear programming at the commencement of the 1960s [nineteen]. This trouble is finding the best solution from a diversity of efficient alternatives of design or operating variables in order to minimize or maximize a desired objective function. In a general mode, the objective function can be the minimization of the operating costs and the undesired fabric production or the maximization of energy efficiency, the yields and operation productivity, the profitability, safety and the reliability of the plant.

Virtually chemical processes are nonlinear and complex, so there are many solutions (in some cases becoming countless) in the optimization bug. Such issues are often as well complex to be solved through slope-based optimization approaches. Evolutionary algorithms (EAs) like GA [twenty], harmony search [21], particle swarm optimization [22] and so on categorized in the AI-based method that is a generic population-based metaheuristic optimization algorithm are capable of efficiently finding an optimal solution in complex issues, such every bit optimization of chemic processes.

Advertisement

4. Application of neural networks in chemical process control

The process control strategies have been adult to better the functioning of the procedure, reduce energy consumption and ensure high prophylactic and environmental goals. The conventional controllers cannot show satisfactory responses in many industrial chemical processes with high nonlinear dynamics and parameter uncertainties, whereas AI approaches can exist effectively controlled for a number of circuitous and nonlinear processes [23].

Because of their high potential for handling nonlinear relationships and self-learning capabilities, there has been considerable interest in the utilize of neural networks for the control in different fields of chemical processes such as thermal processes [24], reaction processes [25] and separation and purification [26, 27].

One of the algorithms based on neural network command is the inverse model control. In this arroyo, it is assumed that the input vector for neural network is the required future or reference output together with the past inputs and the past output variables; the approach tin help to make for better performance the controlled variables when the unmeasured disturbance is present. The manipulated variable of the controlled establish is the output of the neural network controller [23]. In the arrangement with time delay (τ), if the orders of dynamic model for the output and the input are n and m , the changed model can be expressed as the role of the input and output equally shown beneath:

M thou = ∅ y sp y yard − 1 … y thou − n Chiliad m − one − τ … M k − k − τ

E1

where ∅ represents the function of the changed model, k is the discrete time and M , y and ysp are the control action, the output of the plant and the set indicate controller, respectively. Therefore, the controller predicts the control activity, as shown in Figure 3, by having electric current and past values of the procedure model state variables and the by control action.

Figure 3.

Schematic of neural network changed model command.

Fuzzy systems have been used in different applications for decision-making chemical processes [28, 29, 30]. Researchers also used fuzzy logic controller coupled with an optimal control in an exothermic chemical reaction [31], a batch polymerization reactor [32] and polymerization processes [33]. In addition, since time delay can be oft seen in many industrial chemical processes, a possible alternative is the fuzzy model predictive control (FMPC) which has been proposed [34, 35]. In systems with uncertainties of the arrangement model, the option of type-1 fuzzy may non always be the appropriate solution for a control problem [36]. In these cases, the type-ii fuzzy logic control has been represented in many fields of chemical processes [37, 38].

Hybrid controller based on AI strategies combines two or more AI techniques in order to improve control operation of the chemical process. I of the most popular strategies is the adaptive neuro-fuzzy inference arrangement (ANFIS) controller. This approach is a hybrid intelligent system which uses the learning ability of the neural network with the knowledge representation of the fuzzy logic [39]. The schematic of ANFIS model with two inputs (x1 and x2) and one output ( φ ) is shown in Figure iv. Every bit shown in Figure 4, the ANFIS compages contains five layers of feed-forward neural network which are explained as follows:

Figure iv.

Schematic compages of ANFIS model with two fuzzy rules for two inputs and one output.

four.i. First layer

This layer is named as an input layer. Each neuron in this layer saves the parameters of the membership function and well-baked inputs are converted to membership degree values which change between 0 and 1.

4.2. Second layer

Each neuron of this layer performs a connective performance (i.e., "AND") to summate the firing forcefulness of a rule.

four.iii. Third layer

A normalization procedure is performed past the neurons of this layer.

4.four. 4th layer

The normalized firing force is multiplied by a linear combination of the inputs (i.e., Takagi-Sugeno fuzzy rule) in order to obtain a rules layer.

4.5. Fifth layer

The terminal layer of the network is the weighted average of the outputs of the fourth layer.

The application of ANFIS in the process control of chemical plants was seen in the distillation column [twoscore], biodiesel reactor [41].

Advertisement

5. Application of AI techniques in fault detection and diagnosis of chemical engineering

A mistake is defined as a deviation from an acceptable range of an appreciable variable or calculated parameter that is referred to as a failure. A failure can be described every bit variety of malfunctions in the real establish which tin can be caused due to instruments' failures, disturbances and plant parameter uncertainties. The abnormal conditions in a plant tin can result in financial losses. Therefore, in the chemical processes, fault detection and diagnosis take been the focal point of many researches and diverse error detection and diagnosis strategies take been presented in the literature. The mistake diagnostic systems should possess desirable characteristics such as quick detection, isolability, robustness and multiple fault identifiability [42].

One of the intelligent fault diagnosing techniques is neural network systems. Considering of their high potential for capturing nonlinear relationships, neural networks represent a powerful tool for mistake diagnosis [43, 44, 45, 46, 47]. In fault detection based on neural networks, the number of neurons in the input and output layers are equal to the number of measured variables and the number of potential faults in the process, respectively. The outputs of the neural diagnoser are binary variables representing the occurrence of a fault (if the respective value is ane) or the lack of fault occurrence (if the respective value is 0) [47].Another fault diagnosis approach of AI techniques is fuzzy logic, which is applied in chemic processes [48, 49, l, 51]. In fault diagnosis based on fuzzy logic, the fuzzy relations between faults and symptoms are assumed to exist from one to many (i.east., i fault may cause several symptoms). For example:

I f South y m 1 is South 1 , n A Northward D S y m 2 is S ii , n A North D … A N D Southward y 1000 yard is Southward 1000 , n T h eastward n F 1 is H north

where Symi ( i  = one… one thousand ) is the vector of fuzzy input variables (symptoms) and Fi ( j  = one … n ) is the fuzzy output variables (Faults). Si, j is the input linguistic value relevant to jth output and Hj is the output linguistic value. The schematic of a fuzzy mistake detection system is shown in Figure v [51].

Figure 5.

Schematic diagram of a fuzzy error detection scheme.

Although the neural network is a powerful tool for fault diagnosis due to its ability in capturing the nonlinear human relationship with no heuristic reasoning almost process, information technology requires a big number of data corresponding to diverse operating atmospheric condition in which the furnishings of various faults be. On the other hand, the fuzzy diagnoser system expresses the heuristic cognition between the symptoms and their corresponding faults of the process such as linguistic rules and does not crave whatever quantitative data sets corresponding to history and trends of the organisation under whatever operating atmospheric condition [52, 53]. The disadvantage of the fuzzy diagnoser is that managing heuristic and knowledge-based rules is more difficult and fourth dimension demanding and sometimes even impossible for plant-wide integrated processes [54, 55]. Therefore, neuro-fuzzy diagnoser applications in chemical plants are proposed in the literature [56, 57, 58].

In the following, iv illustration studies of AI techniques are presented for various purposes (i.east. modeling, optimization, process control, error detection and diagnosis) of chemical processes.

Analogy case report one: Prediction of virus removal from h2o using microfiltration membrane based on hybrid Mamdani fuzzy and GA.

One of the separation technologies for virus removal from water for municipal effluent reuse is the awarding of membranes. Conventional modeling approaches for predicting membrane performance suffer from diverse limitations such every bit the lack of predictive fouling models or complexities of estimating the properties of the membrane surface and membrane interactions. In this case study, an optimum Mamdani fuzzy model is developed for removal prediction of two types of viruses from water [ii]. The GA is employed for optimal estimation of parameters characterizing the membership functions of the input/output variables of the model. The first pace is defining input/output variables of the model.The amount of virus rejection (R%) which is considered as an output variable of the model is determined as follows:

where Cp and Cf are virus concentrations in permeate and feed, respectively. The input variables of the model are concentration of FMD virus (CFMD), concentration of IBR virus (CIBR), operating pressure level (P), volume (V) and rpm (stirring speed). The experimental data can found in the works of Madaeni and Kurdian [2]. All the variables that exist in the system are discretized past Gaussian-type membership functions.

The next steps are setting a fuzzy inference system using initial fuzzy sets with parameters and defining the fitness part. Two parameters of the Gaussian membership function including x ¯ and σ (Eq. (3)) are obtained via GA.

The mean square fault (MSE) is selected as the fitness function as follows:

where ygrand and ye announce the vector of fuzzy model and data set, respectively.

At that place are two methods for the genetically tuning process. For cases with a low number of rules, the parameters of membership functions in all rules (for both input and output variables) tin be considered equally decision variables through optimization formulation. In this style, a variable at each rule can have different optimized shape membership functions. This approach increases the prediction capability yet at the toll of reducing the interpretability of the model. The second method is used when there are a large number of rules in the model. In this method, each variable of the model in all rules has the aforementioned optimized shape of the membership part. This method has a lower number of decision variables in optimization formulation for the aforementioned example when compared with the beginning method.

According to the possible combination of input variables, x rules can be defined for this model, and due to the low number of rules, the beginning-mentioned method for parameter optimization is applied. The population size and maximum generation number of GA are set as 500 and 100, respectively. Having passed the optimization procedure, the fuzzy model is developed with optimized parameters. This model is developed based on qualitative rules, bypassing the complexities and drawbacks of the white-box modeling method.

The comparison between model information and experimental data shows an accuracy of near 90% for the developed fuzzy model [2].

Illustrative example report two: Optimization of fluidized bed reactor of oxidative coupling of methane based on GA.

In this case study, optimization of C2 (ethane + ethylene) yield in the oxidative coupling of methane (OCM) over the Mn/Na2WOiv/SiO2 goad in a fluidized bed reactor is carried out [twenty].

OCM is a serial of chemical reactions, get-go presented in the 1980s by Keller and Bhasin [59] for the straight conversion of natural gas into the desired production of ethylene and other value-added chemicals. Ane of the barriers to the commercialization of this process is the low yield of the reactions. Various solutions have been proposed for yield improvement in the literature [60, 61]. One possibility to improve the Ctwo yield is phase-wise feeding configuration along the reactor as shown in Figure half dozen [62].

Figure half dozen.

Stage-wise feeding configuration in OCM reactor.

In this scheme, it is assumed that the injected gas in each stage has only oxygen in content and all the marsh gas is introduced to the reactor at the entrance of the bed.

In this example study, the primary process variables which are optimized to heighten Ctwo yield are listed in Table one.

Determination variables Constraints
Methane menses rate (Uc) 0.03–0.v miii/s
Oxygen menstruum rate at each injection function 0.03–0.v one thousand3/s (×0.21)*
Operating temperature (T) 700–850°C
Length of each section of reactor (Li) 0.5–iv one thousand

Table 1.

Determination variables and their constraints.

Note that actually it is the air which entered the bed.


The kinetic model presented by Daneshpayeh et al. [63] is used as the reaction sub-model. The reactor is firstly modeled and and so solved [62]. Afterward, using GA, the Cii yield is optimized for one, two and three secondary injections of oxygen.

Ctwo yield considered every bit the fettle function is defined as follows:

The main GA parameters are presented in Tabular array ii.

Parameter Value
Population size 50
Generations 10,000
Survival probability 0.v
Linear crossover probability 0.5
Mutation probability 0.167

The best results are achieved for three injections of oxygen along the reactor. The optimum values of decision variables are presented in Table 3. The maximum C2 yield of 22.87% is achieved for three secondary oxygen injections at the operating temperature of 746.05°C. This optimized C2 yield which is achieved past an AI-based method is approximately 4% higher than the original model [61].

Decision variable Optimum value
Oxygen period at the beginning of the reactor (m3/s) 0.0833
Oxygen flow at second section of the reactor (chiliad3/s) 0.0500
Oxygen flow at third department of the reactor (one thousand3/due south) 0.0536
Oxygen flow at fourth section of the reactor (grandthree/s) 0.0755
Methane flow at the outset of the reactor (miii/s) 0.3998
Length of first department (one thousand) 0.6345
Length of 2d section (m) 3.9389
Length of 3rd section (chiliad) 0.5882
Length of fourth section (m) ane.0116
Temperature (°C) 746.05
Yield 22.87

Table 3.

Optimum values of conclusion variables at maximum yield.

Illustrative example study iii: Online genetic-ANFIS control for advanced microwave biodiesel reactor.

The microchem reactor based on the microwave process technology is used to produce biodiesel which is practiced for the environment. The reactor temperature should be controlled to ensure an optimal yield of biodiesel and to minimize the generation of unwanted byproducts. For this aim, Wali et al. implemented an artificial intelligent controller design based on the online genetic-ANFIS temperature control for avant-garde biodiesel microwave reactor [41]. The microwave power supply as the manipulated variable, the reactor temperature as control variable and the feed-flow rate every bit the disturbance variable accept been considered in this process.

The online genetic-ANFIS controller has been evaluated at unlike operation conditions (ready-signal tracking and disturbance rejection). The genetic-ANFIS controller successfully tracks the demands of reactor temperature set-point faster than adaptive control without whatever oscillations [41].

Illustrative case study iv: Neuromorphic multiple-error diagnosing the plant-broad system.

In plant-broad systems, because of organization complexity and overlapping symptoms, conventional neural networks operating based on steady-state characteristic data are not unremarkably capable of diagnosing multiple concurrent faults. To overcome this trouble, Tayyebi et al. proposed a new neuromorphic diagnosis framework based on augmented input containing steady-state characteristic data along with newly divers dynamic characteristic information [47]. In this approach, the input vector of the neural network diagnosis has been selected in such a mode that dissimilar faults cause distinctive symptoms. Therefore, information related to both the history of the process and the steady country has been utilized to achieve distinctive symptoms. Accordingly, one can use characteristic points of the dynamic trend of each measured variable to uniquely distinguish and find diverse faults. To evaluate the proposed approach based on the hybrid parameter, the Tennessee Eastman process (TE) that contains large numbers of measurements and manipulated variables and overlapping faults was used as the plant-wide benchmark. The operation of the neuromorphic diagnoser based on the augmented inputs has been compared with that of the conventional neuromorphic diagnostic system whose inputs are steady-state characteristic data. The comparison showed that the proposed method outperformed the conventional neuromorphic diagnoser for the detection of multiple concurrent faults. It was also shown that the proposed scheme can correctly diagnose diverse combinations of half dozen concurrent faults of the TE process (from two to vi simultaneous faults). This achievement reflects the major advantage of the proposed approach, which is its ability to perform fault diagnosis in situations where multiple concurrent faults with overlapping symptoms have occurred [47].

Advertizement

6. Conclusion

AI techniques provide tools to tackle complex issues. Challenging and useful applications of AI techniques have been introduced in the chemical engineering processes. Four illustrative case studies are investigated in fields of procedure modeling, optimization, process control and fault detection and diagnosis. From the clarification of the various applications, the power of AI techniques has been revealed in a wide range of fields in chemical processes.

References

  1. i. Luyben W. Process modeling, simulation and control for chemic engineers. Petroleum Refinery Engineering. 1996;two:289-290
  2. ii. Madaeni SS, Kurdian AR. Fuzzy modeling and hybrid genetic algorithm optimization of virus removal from water using microfiltration membrane. Chemical Engineering Enquiry and Design. 2011;89:456-470
  3. 3. Araromi DO, Sonibare JA, Emuoyibofarhe JO. Fuzzy identification of reactive distillation for acetic acid recovery from waste water. Periodical of Environmental Chemical Engineering science. 2014;two:1394-1403
  4. four. Hajjar Z, Kazemeini M, Rashidi A, Tayyebi S. Artificial intelligence techniques for modeling and optimization of the HDS process over a new graphene based catalyst. Phosphorus, Sulfur, and Silicon and the Related Elements. 2016;191:1256-1261
  5. v. Soltanali South, Halladj R, Tayyebi Due south, Rashidi A. Neural network and genetic algorithm for modeling and optimization of constructive parameters on synthesized ZSM-five particle size. Materials Letters. 2014;136:138-140
  6. 6. Soltanali Southward, Halladj R, Tayyebi S, Rashidi A. Application of genetic-fuzzy approach for interpretation of nano ZSM-5 crystallinity. Materials Letters. 2015;150:39-43
  7. 7. Hajjar Z, Khodadadi A, Mortazavi Y, Tayyebi South, Soltanali Due south. Artificial intelligence modeling of DME conversion to gasoline and light olefins over modified nano ZSM-5 catalysts. Fuel. 2016;179:79-86
  8. 8. Gibbs MS, Morgan Northward, Maier HR, Dandy GC, Nixon JB, Holmes Grand. Investigation into the relationship between chlorine decay and water distribution parameters using information driven methods. Mathematical and Computer Modelling. 2006;44:485-498
  9. 9. Mamdani East, Assilian S. An experiment in linguistic synthesis with a fuzzy logic controller. International Periodical of Human-Car Studies. 1975;7:1-thirteen
  10. 10. Takagi T, Sugeno 1000. Fuzzy identification of systems and its applications to modeling and control. IEEE Transactions on Systems, Man, and Cybernetics. 1985;15:116-132
  11. 11. Zadeh LA. Fuzzy sets equally a basis for a theory of possibility. Fuzzy Sets and Systems. 1978;1:3-28
  12. 12. Adoko AC, Gokceoglu C, Wu Fifty, Zuo QJ. Knowledge-based and information-driven fuzzy modeling for rockburst prediction. International Journal of Stone Mechanics and Mining Sciences. 2013;61:86-95
  13. 13. Sala A, Guerra TM, Babuška R. Perspectives of fuzzy systems and control. Fuzzy Sets and Systems. 2005;156:432-444
  14. 14. Habbi H, Zelmat M, Bouamama BO. A dynamic fuzzy model for a pulsate-boiler-turbine organisation. Automatica. 2003;39:1213-1219
  15. 15. Gudwin R, Gomide F, Pedrycz Due west. Context adaptation in fuzzy processing and genetic algorithms. International Journal of Intelligence Systems. 1998;13:929-948
  16. sixteen. Cordon O, Herrera F, del Jesus MJ, Villar P. A multiobjective genetic algorithm for feature selection and granularity learning in fuzzy-rule based classification systems. In: IFSA World Congr. 20th NAFIPS Int. Conf. 2001. Jt. 9th. 3 2001. pp. 1253-1258
  17. 17. Cordon O, del Jesus MJ, Herrera F. Genetic learning of fuzzy dominion-based classification systems cooperating with fuzzy reasoning methods, International Journal of Intelligence Systems. 1998;13:1025-1053
  18. 18. Pulkkinen P, Koivisto H. A dynamically constrained multiobjective genetic fuzzy organisation for regression problems. IEEE Transactions on Fuzzy Systems. 2010;18:161-177
  19. 19. Chaves I, López J, Zapata J, Robayo A. Process Assay and Simulation in Chemical Engineering. 2016
  20. twenty. Eghbal-Ahmadi Grand-H, Zaerpour Thousand, Daneshpayeh M, Mostoufi N. Optimization of fluidized bed reactor of oxidative coupling of methane. International Journal of Chemical Reactor Engineering. 2012;x:1-21
  21. 21. Yousefi M, Enayatifar R, Darus AN, Abdullah AH. Optimization of plate-fin heat exchangers by an improved harmony search algorithm. Practical Thermal Engineering. 2013;50:877-885
  22. 22. Mahmood HA, Adam Northward, Sahari BB, Masuri SU. Development of a particle swarm optimisation model for estimating the homogeneity of a mixture inside a newly designed CNG-H2-AIR mixer for a dual fuel engine: An experimental and theoretic study. Fuel. 2017;218:131-150
  23. 23. Tayyebi S, Alishiri Thou. The control of MSF desalination plants based on changed model control past neural network. Desalination. 2014;333:92-100
  24. 24. Nowak Grand, Rusin A. Using the artificial neural network to control the steam turbine heating process. Applied Thermal Engineering. 2016;108:204-210
  25. 25. Li Southward, Li Y. Neural network based nonlinear model predictive control for an intensified continuous reactor. Chemical Engineering and Processing. 2015;96:14-27
  26. 26. Fernandez de Canete J, Gonzalez S, del Saz-Orozco P, Garcia I. A harmonic balance approach to robust neural control of MIMO nonlinear processes applied to a distillation column, Periodical of Process Control. 2010;20:1270-1277
  27. 27. Damour C, Benne M, Grondin-Perez B, Chabriat J. Nonlinear predictive control based on artificial neural network model for industrial crystallization. Journal of Food Engineering. 2010;99:225-231
  28. 28. Hojjati H, Sheikhzadeh Thousand, Rohani S. Control of supersaturation in a semibatch antisolvent crystallization process using a fuzzy logic controller. Industrial and Engineering Chemistry Enquiry. 2007;46:1232-1240
  29. 29. Underwood CP. Fuzzy multivariable control of domestic heat pumps. Practical Thermal Engineering. 2015;ninety:957-969
  30. 30. Baroud Z, Benmiloud M, Benalia A, Ocampo-Martinez C. Novel hybrid fuzzy-PID control scheme for air supply in PEM fuel-jail cell-based systems. International Journal of Hydrogen Free energy. 2017;42:10435-10447
  31. 31. Karr CL, Sharma SK, Hatcher WJ, Harper TR. Fuzzy command of an exothermic chemical reaction using genetic algorithms. Engineering science Applications of Artificial Intelligence. 1993;6:575-582
  32. 32. Etinkaya SC, Zeybek Z, Hapoglu H, Alpbaz M. Optimal temperature control in a batch polymerization reactor using fuzzy-relational models-dynamics matrix control. Computers and Chemic Technology. 2006;thirty:1315-1323
  33. 33. Lima NMN, Linan LZ, Filho RM, Wolf Maciel MR, Embiruc M, Grácio u, F. Modeling and predictive command using fuzzy logic: Application for a polymerization system. AIChE Periodical. 2010;56:965-978
  34. 34. Chang 10-H, Yang G-H. Fuzzy robust constrained model predictive command for nonlinear systems. Asian Journal of Control. 2011;13(vi):947-955
  35. 35. Teng L, Wang Y, Cai W, Li H. Robust model predictive control of discrete nonlinear systems with time delays and disturbances via T–S fuzzy approach. Periodical of Process Control. 2017;53:lxx-79
  36. 36. Miccio 1000, Cosenza B. Control of a distillation column by type-two and blazon-1 fuzzy logic PID controllers. Periodical of Process Control. 2014;24:475-484
  37. 37. Galluzzo Yard, Cosenza B. Nonlinear fuzzy control of fed-batch reactor for the penicillin product. Computers and Chemical Technology. 2012;36:273-281
  38. 38. Galluzzo M, Cosenza B. Control of a non-isothermal continuous stirred tank reactor by a feedback-feed frontwards structure using blazon-2 fuzzy logic controllers. Information Sciences. 2011;181:3535-3550
  39. 39. Perendeci A, Arslan Southward, Celebi SS, Tanyolac A. Prediction of effluent quality of an anaerobic treatment found under unsteady country through ANFIS modeling with on-line input variables. Chemical Engineering Journal. 2008;145:78-85
  40. 40. Fernandez de Canete J, Garcia-Cerezo A, Garcia-Moral I, Del Saz P, Ochoa E. Object-oriented arroyo applied to ANFIS modeling and control of a distillation column. Expert Systems with Applications. 2013;40:5648-5660
  41. 41. Wali WA, Al-Shamma AI, Hassan KH, Cullen JD. Online genetic-ANFIS temperature control for advanced microwave biodiesel reactor. Periodical of Process Control. 2012;22:1256-1272
  42. 42. Venkatasubramanian V, Rengaswamy R, Yin K, Kavuri SN. A review of procedure error detection and diagnosis part I: Quantitative model-based methods. Computers and Chemic Engineering. 2003;27:293-311
  43. 43. Tayarani-Bathaie SS, Khorasani G. Fault detection and isolation of gas turbine engines using a bank of neural networks. Journal of Procedure Command. 2015;36:22-41
  44. 44. Tan WL, Nor NM, Abu Bakar MZ, Ahmed Z, Sata SA. Optimum parameters for fault detection and diagnosis arrangement of batch reaction using multiple neural networks. Journal of Loss Prevention in the Procedure Industries. 2012;25:138-141
  45. 45. Behbahani RM, Jazayeri-Rad H, Hajmirzaee South. Fault detection and diagnosis in a sour gas absorption column using neural networks. Chemical Engineering and Technology. 2009;32(5):840-845
  46. 46. Zhang Z, Zhao J. A deep conventionalities network based fault diagnosis model for circuitous chemic processes. Computers & Chemical Engineering. 2017;107:395-407
  47. 47. Tayyebi Due south, Boozarjomehry RB, Shahrokhi M. Neuromorphic multiple-mistake diagnosing organization based on plant dynamic characteristics. Industrial and Technology Chemistry Research. 2013;52:12927-12936
  48. 48. Musulin E, Yélamos I, Puigjaner 50. Integration of principal component analysis and fuzzy logic systems for comprehensive process error detection and diagnosis. Industrial and Technology Chemistry Research. 2006;45:1739-1750
  49. 49. Tarifa EE, Scenna NJ. Fault diagnosis, direct graphs, and fuzzy logic. Computers & Chemical Engineering. 1997;21:S649-S654
  50. 50. Tarifa EE, Scenna NJ. Fault diagnosis for MSF dynamic states using a SDG and fuzzy logic, Error diagnosis for MSF dynamic states using a SDG and fuzzy logic. Desalination. 2004;166:93-101
  51. 51. Tayyebi S, Shahrokhi M, Boozarjomehry RB. Mistake diagnosis in a yeast fermentation bioreactor past genetic fuzzy system. Iranian journal of chemistry and chemical engineering science. 2010;29:61-72
  52. 52. Hang J, Zhang J, Cheng M. Application of multi-form fuzzy support vector auto classifier for error diagnosis of current of air turbine. Fuzzy Sets and Systems. 2016;297:128-140
  53. 53. Jahromi AT, Er MJ, Li X, Lim BS. Sequential fuzzy clustering based dynamic fuzzy neural network for fault diagnosis and prognosis. Neurocomputing. 2016;196:31-41
  54. 54. Vachtsevanos Chiliad, Lewis F, Roemer M. Intelligent Fault Diagnosis and Prognosis for Engineering science Systems. New York: John Wiley & Sons, Inc., Hoboken, New Bailiwick of jersey; 2006
  55. 55. Dou D, Zhou S. Comparison of 4 straight classification methods for intelligent error diagnosis of rotating machinery. Practical Soft Computing. 2016;46:459-468
  56. 56. Lau CK, Heng YS, Hussain MA, Mohamad Nor MI. Fault diagnosis of the polypropylene production procedure (UNIPOL PP) using ANFIS. ISA Transactions. 2010;49:559-566
  57. 57. Bonsignore L, Davarifar One thousand, Rabhi A, Tina GM, Elhajjaji A. Neuro-fuzzy fault detection method for photovoltaic systems. Energy Procedia. 2014;62:431-441
  58. 58. Shabanian One thousand, Montazeri M. A neuro-fuzzy online fault detection and diagnosis algorithm for nonlinear and dynamic systems. International Journal of Control, Automation and Systems. 2011;9:665-670
  59. 59. Keller GE, Bhasin MM. Synthesis of ethylene via oxidative coupling of methane. I. Determination of agile catalysts. Journal of Catalysis. 1982;73:9-nineteen
  60. 60. Kao YK, Lei L, Lin YS. A comparative simulation report on oxidative coupling of methyl hydride in fixed-bed and membrane reactors. Industrial and Engineering Chemistry Inquiry. 1997;36:3583-3593
  61. 61. Lu Y, Dixon AG, Moser WR, Ma YH, Balachandran U. Oxygen-permeable dense membrane reactor for the oxidative coupling of methyl hydride. Journal of Membrane Science. 2000;170:27-34
  62. 62. Daneshpayeh M, Mostoufi N, Khodadadi A, Sotudeh-Gharebagh R, Mortazavi Y. Modeling of stagewise feeding in fluidized bed reactor of oxidative coupling of methane. Energy and Fuels. 2009;23:3745-3752
  63. 63. Daneshpayeh M, Khodadadi A, Mostoufi North, Mortazavi Y, Sotudeh-Gharebagh R, Talebizadeh A. Kinetic modeling of oxidative coupling of methane over Mn/Na2WO4/SiO2 catalyst. Fuel Processing Technology. 2009;ninety:403-410

Written By

Zeinab Hajjar, Shokoufe Tayyebi and Mohammad Hosein Eghbal Ahmadi

Submitted: November 22nd, 2017 Reviewed: February 27th, 2018 Published: June 27th, 2018

© 2018 The Writer(s). Licensee IntechOpen. This chapter is distributed under the terms of the Creative Eatables Attribution 3.0 License, which permits unrestricted utilise, distribution, and reproduction in any medium, provided the original work is properly cited.

jonesthreangster.blogspot.com

Source: https://www.intechopen.com/chapters/60761

0 Response to "Chemical Engineering Process Optimization and Control Methods Literature Review"

ارسال یک نظر

اشتراک در: نظرات پیام (Atom)

Iklan Atas Artikel

Iklan Tengah Artikel 1

Iklan Tengah Artikel 2

Iklan Bawah Artikel