Fuzzy neural networks for control of dynamic systems

This thesis provides a unified and comprehensive treatment of the fuzzy neural networks as the intelligent controllers. This work has been motivated by a need to develop the solid control methodologies capable of coping with the complexity, the nonlinearity, the interactions, and the time variance of the processes under control. In addition, the dynamic behavior of such processes is strongly influenced by the disturbances and the noise, and such processes are characterized by a large degree of uncertainty. Therefore, it is important to integrate an intelligent component to increase the control system ability to extract the functional relationships from the process and to change such relationships to improve the control precision, that is, to display the learning and the reasoning abilities. The objective of this thesis was to develop a self-organizing learning controller for above processes by using a combination of the fuzzy logic and the neural networks. An on-line, direct fuzzy neural controller using the process input-output measurement data and the reference model with both structural and parameter tuning has been developed to fulfill the above objective. A number of practical issues were considered. This includes the dynamic construction of the controller in order to alleviate the bias/variance dilemma, the universal approximation property, and the requirements of the locality and the linearity in the parameters. Several important issues in the intelligent control were also considered such as the overall control scheme, the requirement of the persistency of excitation and the bounded learning rates of the controller for the overall closed loop stability. Other important issues considered in this thesis include the dependence of the generalization ability and the optimization methods on the data distribution, and the requirements for the on-line learning and the feedback structure of the controller. Fuzzy inference specific issues such as the influence of the choice of the defuzzification method, T-norm operator and the membership function on the overall performance of the controller were also discussed. In addition, the e-completeness requirement and the use of the fuzzy similarity measure were also investigated. Main emphasis of the thesis has been on the applications to the real-world problems such as the industrial process control. The applicability of the proposed method has been demonstrated through the empirical studies on several real-world control problems of industrial complexity. This includes the temperature and the number-average molecular weight control in the continuous stirred tank polymerization reactor, and the torsional vibration, the eccentricity, the hardness and the thickness control in the cold rolling mills. Compared to the traditional linear controllers and the dynamically constructed neural network, the proposed fuzzy neural controller shows the highest promise as an effective approach to such nonlinear multi-variable control problems with the strong influence of the disturbances and the noise on the dynamic process behavior. In addition, the applicability of the proposed method beyond the strictly control area has also been investigated, in particular to the data mining and the knowledge elicitation. When compared to the decision tree method and the pruned neural network method for the data mining, the proposed fuzzy neural network is able to achieve a comparable accuracy with a more compact set of rules. In addition, the performance of the proposed fuzzy neural network is much better for the classes with the low occurrences in the data set compared to the decision tree method. Thus, the proposed fuzzy neural network may be very useful in situations where the important information is contained in a small fraction of the available data.

Development of a stable continuous flow immobilized enzyme reactor for the hydrolysis of inulin

A 23.5-fold purified exoinulinase with a specific activity of 413 IU/mg and covalently immobilized on Duolite A568 has been used for the development of a continuous flow immobilized enzyme reactor for the hydrolysis of inulin. In a packed bed reactor containing 72 IU of exoinulinase from Kluyveromyces marxianus YS-1, inulin solution (5%, pH 5.5) with a flow rate of 4 mL/h was completely hydrolyzed at 55 °C. The reactor was run continuously for 75 days and its experimental half-life was 72 days under the optimized operational conditions. The volumetric productivity and fructose yield of the reactor were 44.5 g reducing sugars/L/h and 53.3 g/L, respectively. The hydrolyzed product was a mixture of fructose (95.8%) and glucose (4.2%) having an average fructose/glucose ratio of 24. An attempt has also been made to substitute pure inulin with raw Asparagus racemosus inulin to determine the operational stability of the developed reactor. The system remained operational only for 11 days, where 85.9% hydrolysis of raw inulin was achieved.

Citrus peel influences the production of an extracellular naringinase by Staphylococcus xylosus MAK2 in a stirred tank reactor

Staphylococcus xylosus MAK2, Gram-positive coccus, a nonpathogenic member of the coagulase-negative Staphylococcus family was isolated from soil and used to produce naringinase in a stirred tank reactor. An initial medium at pH 5.5 and a cultivation temperature of 30°C was found to be optimal for enzyme production. The addition of Ca⁺² caused stimulation of enzyme activity. The effect of various physico-chemical parameters, such as pH, temperature, agitation, and inducer concentration was studied. The enzyme production was enhanced by the addition of citrus peel powder (CPP) in the optimized medium. A twofold increase in naringinase production was achieved using different technological combinations. The process optimization using technological combinations allowed rapid optimization of large number of variables, which significantly improved enzyme production in a 5-l reactor in 34 h. An increase in sugar concentration (15 gl^-1) in the fermentation medium further increased naringinase production (8.9 IUml^-1) in the bioreactor. Thus, availability of naringinase renders it attractive for potential biotechnological applications in citrus processing industry.

Acetylation of alcohols and phenols using continuous-flow, tungstosilicic acid-supported, monolith microreactors with scale-up capability

A highly scalable and efficient flow-system has been developed to perform the catalyzed acetylation of alcohols and phenols, such as salicylic acid, at room temperature in excellent yield. The volumetric throughput and the amount of product can be increased simply by increasing the diameter of a versatile catalytic 12-tungstosilicic acid-supported, silica monolith can be used to increase the quantity of product produced without having to changeing the optimal operatingreaction conditions.