Multi-objective Pareto Research Articles

A new multiobjective performance criterion used in PID tuning optimization algorithms

In PID controller design, an optimization algorithm is commonly employed to search for the optimal controller parameters. The optimization algorithm is based on a specific performance criterion which is defined by an objective or cost function. To this end, different objective functions have been proposed in the literature to optimize the response of the controlled system. These functions include numerous weighted time and frequency domain variables. However, for an optimum desired response it is difficult to select the appropriate objective function or identify the best weight values required to optimize the PID controller design. This paper presents a new time domain performance criterion based on the multiobjective Pareto front solutions. The proposed objective function is tested in the PID controller design for an automatic voltage regulator system (AVR) application using particle swarm optimization algorithm. Simulation results show that the proposed performance criterion can highly improve the PID tuning optimization in comparison with traditional objective functions.

Multiobjective Pareto Optimal Design of a Clutch System

Optimum design of a clutch and dual mass flywheel system is completed. Although the clutch systems are exposed to both rotational and axial vibrations, they are generally designed by considering rotational vibrations of engines and they do not have any component to damp axial vibrations due to the following two reasons: first, the package area of the clutch system is very limited and there is no available space to put additional springs and dampers to reduce these vibrations. Second, axial vibrations are normally insignificant to be considered in the analyses and such vibrations are supposed to be damped by the diaphragm spring and cushion springs. Nonetheless, axial vibrations may lead to some unexpected problems in the power train such as the rattle noise that is examined in this study by using global optimization techniques. The components in the clutch system are modeled analytically. Then, by considering the pedal characteristics and vibrations of pressure plate as objective functions, a multi-objective Pareto optimization problem is solved. It is shown that analytical models agree well with the experimental measurements and vibrations in the clutch system can be reduced significantly by choosing the design parameters with optimization tools.

Numerical investigation of a dual-loop EGR split strategy using a split index and multi-objective Pareto optimization

A proposed dual-loop exhaust-gas recirculation (EGR) system that combines the features of high-pressure (HP) and low-pressure (LP) systems is considered a key technology for improving the combustion behavior of diesel engines. The fraction of HP and LP flows, known as the EGR split, for a given dual-loop EGR rate play an important role in determining the engine performance and emission characteristics. Therefore, identifying the proper EGR split is important for the engine optimization and calibration processes, which affect the EGR response and deNOX efficiencies. The objective of this research was to develop a dual-loop EGR split strategy using numerical analysis and one-dimensional (1D) cycle simulation. A control system was modeled by coupling the 1D cycle simulation and the control logic. An EGR split index was developed to investigate the HP/LP split effects on the engine performance and emissions. Using the model-based control system, a multi-objective Pareto (MOP) analysis was used to minimize the NOX formation and fuel consumption through optimized engine operating parameters. The MOP analysis was performed using a response surface model extracted from Latin hypercube sampling as a fractional factorial design of experiment. By using an LP rich dual-loop EGR, a high EGR rate was attained at low, medium, and high engine speeds, increasing the applicable load ranges compared to base conditions.

Critical Assessment 3: The unique contributions of multi-objective evolutionary and genetic algorithms in materials research

The current state of the art of materials research using multi-objective genetic and evolutionary algorithms is briefly presented with critical analyses. The basic concepts of multi-objective optimisation and Pareto optimality are explained in simple terms and the advantages of an evolutionary approach are emphasised. Current materials related research in this area is summarised, focusing on the achievements to date and the specific needs for further improvement.

Reducing Energy Consumption in Pharmaceutical Production Processes: Framework and Case Study

This paper aims to present a novel framework for reducing energy consumption in pharmaceutical manufacturing processes, with a primary focus on parenterals production. The framework supports (a) the design of optimal energy-saving solutions, (b) the execution and implementation and (c) the comparison of designed and actual performance as a post-implementation control. In selecting promising options, multiobjective criteria are defined for comprehensive decision-making which considers not only energy savings, but also other aspects such as good manufacturing practice (GMP), risk, and workers’ safety. In the framework, five phases were defined in total, with three for design and two for execution and control, respectively. In the three design phases, options are generated, evaluated and selected step by step, with appropriate evaluation criteria covering financial as well as non-financial aspects. The roles of various stakeholders, e.g., Operations, Engineering, or Quality Assurance, are defined for each phase in order to enable smooth and certain decision-making. A case study was performed in the parenterals production plant at Hoffmann-La Roche in Kaiseraugst. Twelve energy efficiency ideas were generated and, after the screening and selection process, the three most promising options from the multiobjective Pareto optimization were implemented to reduce the total plant’s energy consumption by 2.5 %. The framework enabled the systematic generation and selection of various options, which helped in the allocation of company resources in a prioritized and thus effective manner.

Multi-objective optimal design of online PID controllers using model predictive control based on the group method of data handling-type neural networks

In this paper, model predictive control (MPC) is used for optimal selection of proportional-integral-derivative (PID) controller gains. In conventional tuning methods a history of response error of the system under control in the passed time is measured and used to adjust PID parameters in order to improve the performance of the system in proceeding time. But MPC obviates this characteristic of classic PID. In fact MPC tries to tune the controller by predicting the system's behaviour some time steps ahead. In this way, PID parameters are adjusted before any real error occurs in the system's response. For this purpose, polynomial meta-models based on the evolved group method of data handling neural networks are obtained to simply simulate the time response of the dynamic system. Moreover, a non-dominated sorting genetic algorithm has been used in a multi-objective Pareto optimisation to select the parameters of the MPC which are prediction horizon, control horizon and relation of weight of Δ u and error, to minimise simultaneously two objective functions that are control effort and integral time absolute error of the system response. The results mentioned at the end obviously declare that the proposed method surpasses conventional tuning methods for PID controllers, and Pareto optimal selection of predictive parameters also improves the performance of the introduced method.

Optimization of Reactive Power Based on Dynamic Learning Factor Multi-Objective Particle Swarm Algorithm

. Particle swarm optimization algorithm has the defects of easy to fall into local optimum and low convergence accuracy used in reactive power optimization. To solve the problems, this paper proposed an improved particle swarm optimization algorithm based on dynamic learning factors. The two accelerations are changed with searching stage, so as to enhance the early globle search ability and the late local search ability, then to avoid local optimum; minimum particle angle method and crowded distance method are uesd to determine the global extremum in instalments, so as to improve the convergence speed and accuracy of multi-objective pareto solutions. Take the IEEE 30 bus system IEEE 118 bus system as example, the proposed method is compared with adaptive chaos particle swarm optimization (ACPSO) and NSGA-II, simulation results show that the method put forward in this paper has better convergence accuracy.

Numerical analysis of a dual-fueled CI (compression ignition) engine using Latin hypercube sampling and multi-objective Pareto optimization

Diesel/natural gas dual-fuel engines were studied numerically using Latin hypercube sampling (LHS) and multi-objective Pareto optimization. The combustion characteristics were analyzed and performance metrics studied as a function of the exhaust gas recirculation (EGR) fraction, compression ratio, injection timing, and natural gas fraction (NGF). The fundamental effects of the NGF on the in-cylinder pressure, peak temperature, brake torque, and brake specific fuel consumption (BSFC) were investigated. Regression coefficients were obtained using LHS to describe the sensitivity of the brake torque, BSFC, and brake specific NOX (BSNOX) emission levels to the operating parameters. A response surface was found using Pareto optimization. The dominant parameters affecting the brake torque, BSFC, and BSNOX were the compression ratio and EGR fraction.

Software Defect Prediction Based on GUHA Data Mining Procedure and Multi-Objective Pareto Efficient Rule Selection

Software defect prediction, if is effective, enables the developers to distribute their testing efforts efficiently and let them focus on defect prone modules. It would be very resource consuming to test all the modules while the defect lies in fraction of modules. Information about fault-proneness of classes and methods can be used to develop new strategies which can help mitigate the overall development cost and increase the customer satisfaction. Several machine learning strategies have been used in recent past to identify defective modules. These models are built using publicly available historical software defect data sets. Most of the proposed techniques are not able to deal with the class imbalance problem efficiently. Therefore, it is necessary to develop a prediction model which consists of small simple and comprehensible rules. Considering these facts, in this paper, the authors propose a novel defect prediction approach named GUHA based Classification Association Rule Mining algorithm (G-CARM) where “GUHA” stands for General Unary Hypothesis Automaton. G-CARM approach is primarily based on Classification Association Rule Mining, and deploys a two stage process involving attribute discretization, and rule generation using GUHA. GUHA is oldest yet very powerful method of pattern mining. The basic idea of GUHA procedure is to mine the interesting attribute patterns that indicate defect proneness. The new method has been compared against five other models reported in recent literature viz. Naive Bayes, Support Vector Machine, RIPPER, J48 and Nearest Neighbour classifier by using several measures, including AUC and probability of detection. The experimental results indicate that the prediction performance of G-CARM approach is better than other prediction approaches. The authors' approach achieved 76% mean recall and 83% mean precision for defective modules and 93% mean recall and 83% mean precision for non-defective modules on CM1, KC1, KC2 and Eclipse data sets. Further defect rule generation process often generates a large number of rules which require considerable efforts while using these rules as a defect predictor, hence, a rule sub-set selection process is also proposed to select best set of rules according to the requirements. Evolution criteria for defect prediction like sensitivity, specificity, precision often compete against each other. It is therefore, important to use multi-objective optimization algorithms for selecting prediction rules. In this paper the authors report prediction rules that are Pareto efficient in the sense that no further improvements in the rule set is possible without sacrificing some performance criteria. Non-Dominated Sorting Genetic Algorithm has been used to find Pareto front and defect prediction rules.

Control Optimization of a Slotted Switched Reluctance Generator for High-torque Applications

This article describes the control optimization of a slotted switched reluctance generator for low-speed applications. The machine is simulated with the finite-element method. The turn-off and turn-on angles are optimized by means of a genetic algorithm to maximize the output power and minimize the torque ripple. First, these two criteria are optimized separately with a mono-objective genetic algorithm, and then a multi-objective Pareto genetic algorithm is used. An analysis of optimized parameters and resulting current waveforms is also performed. Experimental results based on a 6/4 switched reluctance generator are also presented.

An analysis of accuracy-diversity trade-off for hybrid combined system with multiobjective predictor selection

This study examines the contribution of diversity under a multi-objective context for the promotion of learners in an evolutionary system that generates combinations of partially trained learners. The examined system uses a grammar-driven genetic programming to evolve hierarchical, multi-component combinations of multilayer perceptrons and support vector machines for regression. Two advances are studied. First, a ranking formula is developed for the selection probability of the base learners. This formula incorporates both a diversity measure and the performance of learners, and it is tried over a series of artificial and real-world problems. Results show that when the diversity of a learner is incorporated with equal weights to the learner performance in the evolutionary selection process, the system is able to provide statistically significantly better generalization. The second advance examined is a substitution phase for learners that are over-dominated, under a multi-objective Pareto domination assessment scheme. Results here show that the substitution does not improve significantly the system performance, thus the exclusion of very weak learners, is not a compelling task for the examined framework.

Approximate multi-objective optimization using conservative and feasible moving least squares method: application to automotive knuckle design

The original version of the moving least squares method (MLSM) does not always ensure solution feasibility for nonlinear and/or non-convex functions in the context of meta-model-based approximate optimization. The paper explores a new implementation of MLSM that ensures the conservative feasibility of Pareto optimal solutions in non-dominated sorting genetic algorithm (NSGA-II)-based approximate multi-objective optimization. We devised a `conservative and feasible MLSM' (CF-MLSM) to realize the conservativeness and feasibility of multi-objective Pareto optimal solutions for both unconstrained and constrained problems. We verified the usefulness of our proposed approach by exploring strength-based sizing optimization of an automotive knuckle component under bump and brake loading constraints.

Multi-objective stochastic-structural-optimization of shape-memory-alloy assisted pure-friction bearing for isolating building against random earthquakes

The optimal stochastic performance of pure friction system supplemented with SMA-restrainer (SMA-PF) is presented based on a framework of multi-objective optimization. The evaluation of system response for this is based on nonlinear random vibration analysis. The optimizing design variables are based on two mutually conflicting objectives, involving maximizing the isolation efficiency as well as isolator displacement. The proposed optimal design, thus, not only maximizes the isolation efficiency but also impose due consideration to the bearing displacement. The optimal bearing is shown to substantially reduce the bearing displacement with nominal sacrifice in isolation efficiency. Comparison of the multi-objective Pareto fronts reveals much facilitated trade-off among the mutually conflicting objectives in SMA-PF than in PF system. The viability of the optimal performance is further verified under recorded ground motions, which is observed to be in parity to the stochastic response behavior. The reduction in the residual bearing displacement is also observed.

Particle Swarm Optimization and strength pareto to solve multiobjective optimization problems

Many attempts have been made to extend Particle Swarm Optimization to solve Multiobjective Problems. In this paper, the Strength Pareto concept, proposed by Zitzler, is incorporated to a Particle Swarm Optimization to build a new approach to solve Multiobjective Optimization Problems, the Multiobjective Strength Pareto Particle Swarm Optimization. Numerical results are reported to validate the proposed method to solve some unconstrained benchmarks problems and a constrained design of a brushless direct current motor.

Reliability-based optimal controller design for systems with probabilistic uncertain parameters using fuzzy limit state function

In this paper, a fuzzy rule-based system (FRS) has been used for optimal reliability-based robust controller design for a two-mass-spring system with probabilistic uncertainties in its parameters. In this way, a multiobjective uniform-diversity genetic algorithm (MUGA) is first used to find a Pareto front of two-mass-spring system in a deterministic approach. This paper considers a two-mass-spring system under an impulse input. Two conflicting objective functions in this model include settling time of the second mass and control effort exerted on the first mass. Consequently, such Pareto front is then obtained for a two-mass-spring system with probabilistic uncertainties in its parameters using the probabilities of failure of those objective functions through a Monte Carlo simulation approach. It is shown that the FRS system removes the difficulty of selecting suitable crisp values and obligation due to a defining limit state function. Besides, the multiobjective Pareto optimization of such robust controllers using MUGA unveils some very important and informative trade-offs among those objective functions. Consequently, some optimum robust controllers can be compromisingly chosen from the Pareto frontiers.

Modeling and Optimization of Poly Electrolyte Dosage in Water Treatment Process by GMDH Type- NN and MOGA

Coagulation-flocculation is the most important parts of water treatment process. Traditionally, optimum pre coagulant dosage is determined by used jar tests in laboratory. However; jar tests are time-consuming, expensive, and less adaptive to changes in raw water quality in real time. Soft computing can be used to overcome these limitations. In this paper, multi-objective evolutionary Pareto optimal design of GMDH Type-Neural Network has been used for modeling and predicting of optimum poly electrolyte dosage in Rasht WTP, Guilan, Iran, using Input - output data sets. In this way, multi-objective uniform-diversity genetic algorithms (MUGA) are then used for Pareto optimization of GMDH networks. In order to achieve this modeling, the experimental data were divided into train and test sections. The predicted values were compared with those of experimental values in order to estimate the performance of the GMDH network. Also, Multi Objective Genetic Algorithms (MOGA) are then used for optimization of influence parameters in pre coagulant (Poly electrolyte) dosage.

Design and Evaluation of Soft Keyboards for Brahmic Scripts

Despite being spoken by a large percentage of the world, Indic languages in general lack user-friendly and efficient methods for text input. These languages have poor or no support for typing. Soft keyboards, because of their ease of installation and lack of reliance on specific hardware, are a promising solution as an input device for many languages. Developing an acceptable soft keyboard requires the frequency analysis of characters in order to design a layout that minimizes text-input time. This article proposes the use of various development techniques, layout variations, and evaluation methods for the creation of soft keyboards for Brahmic scripts. We propose that using optimization techniques such as genetic algorithms and multi-objective Pareto optimization to develop multi-layer keyboards will increase the speed at which text can be entered.

A Review of Recent Developments in Electrical Machine Design Optimization Methods With a Permanent-Magnet Synchronous Motor Benchmark Study

This paper systematically covers the significant developments of the last decade, including surrogate modeling of electrical machines and direct and stochastic search algorithms for both single- and multi-objective design optimization problems. The specific challenges and the dedicated algorithms for electric machine design are discussed, followed by benchmark studies comparing response surface (RS) and differential evolution (DE) algorithms on a permanent-magnet-synchronous-motor design with five independent variables and a strong nonlinear multiobjective Pareto front and on a function with eleven independent variables. The results show that RS and DE are comparable when the optimization employs only a small number of candidate designs and DE performs better when more candidates are considered.

Predicting beach profile evolution with group method data handling-type neural networks on beaches with seawalls

A major goal of coastal engineering is to develop models for the reliable prediction of short- and long-term near shore evolution. The most successful coastal models are numerical models, which allow flexibility in the choice of initial and boundary conditions. In the present study, evolutionary algorithms (EAs) are employed for multi-objective Pareto optimum design of group method data handling (GMDH)-type neural networks that have been used for bed evolution modeling in the surf zone for reflective beaches, based on the irregular wave experiments performed at the Hydraulic Laboratory of Imperial College (London, UK). The input parameters used for such modeling are significant wave height, wave period, wave action duration, reflection coefficient, distance from shoreline and sand size. In this way, EAs with an encoding scheme are presented for evolutionary design of the generalized GMDH-type neural networks, in which the connectivity configurations in such networks are not limited to adjacent layers. Also, multi-objective EAs with a diversity preserving mechanism are used for Pareto optimization of such GMDH-type neural networks. The most important objectives of GMDH-type neural networks that are considered in this study are training error (TE), prediction error (PE), and number of neurons (N). Different pairs of these objective functions are selected for two-objective optimization processes. Therefore, optimal Pareto fronts of such models are obtained in each case, which exhibit the trade-offs between the corresponding pair of the objectives and, thus, provide different non-dominated optimal choices of GMDH-type neural network model for beach profile evolution. The results showed that the present model has been successfully used to optimally prediction of beach profile evolution on beaches with seawalls.

Multi-Objective Pareto Optimization of Double-Station Milling Process with the Use of PSO Algorithm

In the paper,a new hybrid optimization technique for multi-objective optimization of surface milling is proposed. The developed approach is based on enhanced Pareto particle swarm optimization algorithm. The optimization of double-station milling is investigated basing on the available model in terms of two objectives: spindle power and production time. The final result is not a single solution but a whole set. In order to obtain satisfied Pareto set, multi-objective evolutionary algorithm for rail milling problem (MOEA-RMP) is used. An illustrative example was used to demonstrate effectiveness and applicability of the proposed approach.