Genetic algorithms for local controller network construction

Local Controller Networks (LCNs) provide nonlinear control by interpolating between a set of locally valid, subcontrollers covering the operating range of the plant. Constructing such networks typically requires knowledge of valid local models. This paper describes a new genetic learning approach to the construction of LCNs directly from the dynamic equations of the plant, or from modelling data. The advantage is that a priori knowledge about valid local models is not needed. In addition to allowing simultaneous optimisation of both the controller and validation function parameters, the approach aids transparency by ensuring that each local controller acts independently of the rest at its operating point. It thus is valuable for simultaneous design of the LCNs and identification of the operating regimes of an unknown plant. Application results from a highly nonlinear pH neutralisation process and its associated neural network representation are utilised to illustrate these issues.

Genetic programming based formulation for fresh and hardened properties of self-compacting concrete containing pulverised fuel ash

Self-compacting concrete (SCC) flows into place and around obstructions under its own weight to fill the formwork completely and self-compact without any segregation and blocking. Elimination of the need for compaction leads to better quality concrete and substantial improvement of working conditions. This investigation aimed to show possible applicability of genetic programming (GP) to model and formulate the fresh and hardened properties of self-compacting concrete (SCC) containing pulverised fuel ash (PFA) based on experimental data. Twenty-six mixes were made with 0.38 to 0.72 water-to-binder ratio (W/B), 183–317 kg/m³ of cement content, 29–261 kg/m³ of PFA, and 0 to 1% of superplasticizer, by mass of powder. Parameters of SCC mixes modelled by genetic programming were the slump flow, JRing combined to the Orimet, JRing combined to cone, and the compressive strength at 7, 28 and 90 days. GP is constructed of training and testing data using the experimental results obtained in this study. The results of genetic programming models are compared with experimental results and are found to be quite accurate. GP has showed a strong potential as a feasible tool for modelling the fresh properties and the compressive strength of SCC containing PFA and produced analytical prediction of these properties as a function as the mix ingredients. Results showed that the GP model thus developed is not only capable of accurately predicting the slump flow, JRing combined to the Orimet, JRing combined to cone, and the compressive strength used in the training process, but it can also effectively predict the above properties for new mixes designed within the practical range with the variation of mix ingredients.

Dynamic evolution of the genetic search region through fuzzy coding

A technique for automatic exploration of the genetic search region through fuzzy coding (Sharma and Irwin, 2003) has been proposed. Fuzzy coding (FC) provides the value of a variable on the basis of the optimum number of selected fuzzy sets and their effectiveness in terms of degree-of-membership. It is an indirect encoding method and has been shown to perform better than other conventional binary, Gray and floating-point encoding methods. However, the static range of the membership functions is a major problem in fuzzy coding, resulting in longer times to arrive at an optimum solution in large or complicated search spaces. This paper proposes a new algorithm, called fuzzy coding with a dynamic range (FCDR), which dynamically allocates the range of the variables to evolve an effective search region, thereby achieving faster convergence. Results are presented for two benchmark optimisation problems, and also for a case study involving neural identification of a highly non-linear pH neutralisation process from experimental data. It is shown that dynamic exploration of the genetic search region is effective for parameter optimisation in problems where the search space is complicated.

Optimal proportional-integral-derivative control of shape memory alloy actuators using genetic algorithm and the Preisach model

Shape memory alloy (SMA) actuators, which have the ability to return to a predetermined shape when heated, have many potential applications in aeronautics, surgical tools, robotics, and so on. Although the number of applications is increasing, there has been limited success in precise motion control owing to the hysteresis effect of these smart actuators. The present paper proposes an optimization of the proportional-integral-derivative (PID) control method for SMA actuators by using genetic algorithm and the Preisach hysteresis model.

Modelling and Control of Shape Memory Alloy Actuators by using Preisach Model, Genetic Algorithm and Fuzzy Logic

Shapememoryalloy (SMA) actuators, which have the ability to return to a predetermined shape when heated, have many potential applications in aeronautics, surgical tools, robotics and so on. Nonlinearity hysteresis effects existing in SMA actuators present a problem in the motion control of these smart actuators. This paper investigates the control problem of SMA actuators in both simulation and experiment. In the simulation, the numerical Preisachmodel with geometrical interpretation is used for hysteresis modeling of SMA actuators. This model is then incorporated in a closed loop PID control strategy. The optimal values of PID parameters are determined by using geneticalgorithm to minimize the mean squared error between desired output displacement and simulated output. However, the control performance is not good compared with the simulation results when these parameters are applied to the real SMA control since the system is disturbed by unknown factors and changes in the surrounding environment of the system. A further automated readjustment of the PID parameters using fuzzylogic is proposed for compensating the limitation. To demonstrate the effectiveness of the proposed controller, real time control experiment results are presented.

On the application of genetic algorithms for optimising composites against impact loading

A genetic algorithm (GA) was adopted to optimise the response of a composite laminate subject to impact. Two different impact scenarios are presented: low-velocity impact of a slender laminated strip and high-velocity impact of a rectangular plate by a spherical impactor. In these cases, the GA's objective was to, respectively, minimise the peak deflection and minimise penetration by varying the ply angles.

The GA was coupled to a commercial finite-element (FE) package LS DYNA to perform the impact analyses. A comparison with a commercial optimisation package, LS OPT, was also made. The results showed that the GA was a robust, capable optimisation tool that produced near optimal designs, and performed well with respect to LS OPT for the more complex high-velocity impact scenario tested.

Optimal design of cold-formed steel portal frames for stressed-skin action using genetic algorithm

This paper describes a stressed-skin diaphragm approach to the optimal design of the internal frame of a cold-formed steel portal framing system, in conjunction with the effect of semi-rigid joints. Both ultimate and serviceability limit states are considered. Wind load combinations are included. The designs are optimized using a real-coded niching genetic algorithm, in which both discrete and continuous decision variables are processed. For a building with two internal frames, it is shown that the material cost of the internal frame can be reduced by as much as 53%, compared with a design that ignores stressed-skin action.

Codon ambiguities as a mechanism to alter the genetic code in Saccharomyces cerevisiae

Although the genetic code is generally viewed as immutable, alterations to its standard form occur in the three domains of life. A remarkable alteration to the standard genetic code occurs in many fungi of the Saccharomycotina CTG clade where the Leucine CUG codon has been reassigned to Serine by a novel transfer RNA (Ser-tRNACAG). The host laboratory made a major breakthrough by reversing this atypical genetic code alteration in the human pathogen Candida albicans using a combination of tRNA engineering, gene recombination and forced evolution. These results raised the hypothesis that synthetic codon ambiguities combined with experimental evolution may release codons from their frozen state. In this thesis we tested this hypothesis using S. cerevisiae as a model system. We generated ambiguity at specific codons in a two-step approach, involving deletion of tRNA genes followed by expression of non-cognate tRNAs that are able to compensate the deleted tRNA. Driven by the notion that rare codons are more susceptible to reassignment than those that are frequently used, we used two deletion strains where there is no cognate tRNA to decode the rare CUC-Leu codon and AGG-Arg codon. We exploited the vulnerability of the latter by engineering mutant tRNAs that misincorporate Ser at these sites. These recombinant strains were evolved over time using experimental evolution. Although there was a strong negative impact on the growth rate of strains expressing mutant tRNAs at high level, such expression at low level had little effect on cell fitness. We found that not only codon ambiguity, but also destabilization of the endogenous tRNA pool has a strong negative impact in growth rate. After evolution, strains expressing the mutant tRNA at high level recovered significantly in several growth parameters, showing that these strains adapt and exhibit higher tolerance to codon ambiguity. A fluorescent reporter system allowing the monitoring of Ser misincorporation showed that serine was indeed incorporated and possibly codon reassignment was achieved. Beside the overall negative consequences of codon ambiguity, we demonstrated that codons that tolerate the loss of their cognate tRNA can also tolerate high Ser misincorporation. This raises the hypothesis that these codons can be reassigned to standard and eventually to new amino acids for the production of proteins with novel properties, contributing to the field of synthetic biology and biotechnology.

Application of computational intelligence to engineering

Computational Intelligence (CI) includes four main areas: Evolutionary Computation (genetic algorithms and genetic programming), Swarm Intelligence, Fuzzy Systems and Neural Networks. This article shows how CI techniques overpass the strict limits of Artificial Intelligence field and can help solving real problems from distinct engineering areas: Mechanical, Computer Science and Electrical Engineering.

Application of genetic algorithms in the design of an electrical potential of fractional order

Fractional calculus (FC) is currently being applied in many areas of science and technology. In fact, this mathematical concept helps the researches to have a deeper insight about several phenomena that integer order models overlook. Genetic algorithms (GA) are an important tool to solve optimization problems that occur in engineering. This methodology applies the concepts that describe biological evolution to obtain optimal solution in many different applications. In this line of thought, in this work we use the FC and the GA concepts to implement the electrical fractional order potential. The performance of the GA scheme, and the convergence of the resulting approximation, are analyzed. The results are analyzed for different number of charges and several fractional orders.

Evolutionary switch and genetic convergence on rbcL following the evolution of C4 photosynthesis.

Rubisco is responsible for the fixation of CO2 into organic compounds through photosynthesis and thus has a great agronomic importance. It is well established that this enzyme suffers from a slow catalysis, and its low specificity results into photorespiration, which is considered as an energy waste for the plant. However, natural variations exist, and some Rubisco lineages, such as in C4 plants, exhibit higher catalytic efficiencies coupled to lower specificities. These C4 kinetics could have evolved as an adaptation to the higher CO2 concentration present in C4 photosynthetic cells. In this study, using phylogenetic analyses on a large data set of C3 and C4 monocots, we showed that the rbcL gene, which encodes the large subunit of Rubisco, evolved under positive selection in independent C4 lineages. This confirms that selective pressures on Rubisco have been switched in C4 plants by the high CO2 environment prevailing in their photosynthetic cells. Eight rbcL codons evolving under positive selection in C4 clades were involved in parallel changes among the 23 independent monocot C4 lineages included in this study. These amino acids are potentially responsible for the C4 kinetics, and their identification opens new roads for human-directed Rubisco engineering. The introgression of C4-like high-efficiency Rubisco would strongly enhance C3 crop yields in the future CO2-enriched atmosphere.