Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The company's sustainable competitive advantage derives from its capacity to create value for customers and to adapt the operational practices to changing situations. Business processes are the heart of each company. Therefore process excellence has become a key issue. This book introduces a novel approach focusing on the autonomous optimization of business processes by applying sophisticated machine learning techniques such as Relational Reinforcement Learning and Particle Swarm Optimization.

Process Flexibility --- Business Process Modeling --- Relational Reinforcement Learning --- Optimization --- Particle Swarm Optimization

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This Master’s Thesis aims to produce a tubular permanent magnet actuator (TPMA) design capable of replacing the hydraulic dampers present in active train suspensions. This design needs to be optimised to provide the best possible performance.
In the first part of this thesis, a state of the art of the available TPMA topologies is presented as
well as their operating principle. 
In the second part the analytical model of each topology is developed in order to obtain the behaviour of the magnetic flux within each actuator. This model contains the solution of the Laplace and Poisson equations from Maxwell’s equations. The specific boundary conditions for each of the
topologies are exposed in order to obtain the specific solutions. Then the results are compared in order to keep the best topology for the rest of the thesis.
The third part is devoted to the modelling of the thrust produced by the actuator. The thrust
produced by the actuator is dependent on the type of current injected. Thus three types of current are compared: single-phase, two-phase and three-phase.
The fourth part concerns the optimisation of the actuator design. In a first step, the optimisation is
done by the particle swarm optimisation (PSO) method. This first optimisation has only one objective, to maximise the thrust produced by the actuator. The dimensions to be optimised are the radii of the actuator and the pole pitch of the magnets. In a second step, a new objective, that of minimising the force variation, is added to the optimisation. This multi-objective optimisation problem is solved using a method derived from PSO: vector evaluated particle swarm optimisation. Finally, the different designs obtained by the two optimisations are compared.
The last part is devoted to the presentation of some improvements that could be made to the analytical model of the actuator to make it even more accurate.

Tubular permanent magnet actuator --- Linear machine --- Particle swarm optimisation --- Dual Halbach array --- Analytical model --- Ingénierie, informatique & technologie > Ingénierie mécanique

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Evolutionary algorithms and metaheuristics are widely used to provide efficient and effective approximate solutions to computationally hard optimization problems. With the widespread use of intelligent systems in recent years, evolutionary algorithms have been applied, beyond classical optimization problems, to AI system parameter optimization and the design of artificial neural networks and feature selection in machine learning systems. This volume will present recent results of applications of the most successful metaheuristics, from differential evolution and particle swarm optimization to artificial neural networks, loT allocation, and multi-objective optimization problems. It will also provide a broad view of the role and the potential of evolutionary algorithms as service components in Al systems.

multi-objective optimization problems --- particle swarm optimization (PSO) --- Gaussian mutation --- improved learning strategy --- big data --- interval concept lattice --- horizontal union --- sequence traversal --- evolutionary algorithms --- multi-objective optimization --- parameter puning --- parameter analysis --- particle swarm optimization --- differential evolution --- global continuous optimization --- wireless sensor networks --- task allocation --- stochastic optimization --- social network optimization --- memetic particle swarm optimization --- adaptive local search operator --- co-evolution --- PSO --- formal methods in evolutionary algorithms --- self-adaptive differential evolutionary algorithms --- constrained optimization --- ensemble of constraint handling techniques --- hybrid algorithms --- association rules --- mining algorithm --- vertical union --- neuroevolution --- neural networks --- n/a

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Today, modern Geotechnical Engineers, who in the past would have considered the phenomena occurring in the (primarily soil) environment, are faced with developments in environmental sciences that are becoming increasingly more detailed and sophisticated, with the natural phenomena and processes surrounding the civil engineering infrastructure being modeled, designed, monitored, and assessed in a more holistic way. This book brings together the state of the art in geotechnics with a focus on sustainable design, resilience, construction, and monitoring of the performance of geotechnical assets from ground investigations, through foundation and drainage design to soil stabilization and reinforcement. Engineers and scientists working in the fields of green infrastructure, nature-based solutions, sustainable drainage, eco-engineering, hydro-geology, landscape planning, plant science, environmental biology or bio-chemistry, earth sciences, GIS, and remote sensing are represented here by articles that show significant geotechnical components or applications. Case studies showcasing the application of the sustainable development principles (e.g., reuse, recycle, reduce; stakeholder engagement; public health; UN Global Sustainability Goals) in Geotechnics are also included in this book.

machine learning --- random forest --- particle swarm optimization --- Vietnam --- Seepage --- Earth-fill dam --- Experimental analysis --- Numerical analysis --- SEEP/W model --- Dam safety and sustainability --- highway construction --- environmental protection --- soil loss --- erosion control --- risk --- hazard --- vulnerability --- landslides --- multicriteria assessment --- analytical hierarchy process --- calcium sulfoaluminate cement --- stabilized soil --- unconfined compressive strength --- hydration products --- microstructure --- sustainability --- geosynthetics --- poly(lactic acid) --- biopolymers --- geogrids --- tensile strength --- n/a

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Standalone (off-grid) renewable energy systems supply electricity in places where there is no access to a standard electrical grid. These systems may include photovoltaic generators, wind turbines, hydro turbines or any other renewable electrical generator. Usually, this kind of system includes electricity storage (commonly lead-acid batteries, but also other types of storage can be used). In some cases, a backup generator (usually powered by fossil fuel, diesel or gasoline) is part of the hybrid system. The modelling of the components, the control of the system and the simulation of the performance of the whole system are necessary to evaluate the system technically and economically. The optimization of the sizing and/or the control is also an important task in this kind of system.

Research & information: general --- renewable energy --- low-temperature energy storage --- SOC --- simulation --- sustainability --- greenhouse gas emission --- economic feasibility --- photovoltaic systems --- MPPT --- partial shading condition --- transfer reinforcement learning --- space decomposition --- microgrids --- energy management --- optimization --- photovoltaic --- energy storage --- demand response program (DRP) --- photovoltaic system (PV) --- pumped heat energy storage (PHES) --- critical peak pricing (CPP) DRP --- time-ahead dynamic pricing (TADP) DRP --- loss of power supply probability (LPSP) --- energy storage system (ESS) --- Multi-Objective Particle Swarm Optimization (MOPSO) --- pitch control --- permanent magnet-synchronous generator (PMSG) --- limit extracted power --- nonlinear adaptive control (NAC) --- perturbation observer --- vanadium redox flow battery --- genetic algorithm --- binary particle swarm optimization --- time-varying mirrored S-shaped transfer function --- greenhouse gas emissions --- heliostat --- sun tracking --- solar energy --- embedded system --- fuzzy logic control --- center of sums defuzzification method --- renewable energy --- low-temperature energy storage --- SOC --- simulation --- sustainability --- greenhouse gas emission --- economic feasibility --- photovoltaic systems --- MPPT --- partial shading condition --- transfer reinforcement learning --- space decomposition --- microgrids --- energy management --- optimization --- photovoltaic --- energy storage --- demand response program (DRP) --- photovoltaic system (PV) --- pumped heat energy storage (PHES) --- critical peak pricing (CPP) DRP --- time-ahead dynamic pricing (TADP) DRP --- loss of power supply probability (LPSP) --- energy storage system (ESS) --- Multi-Objective Particle Swarm Optimization (MOPSO) --- pitch control --- permanent magnet-synchronous generator (PMSG) --- limit extracted power --- nonlinear adaptive control (NAC) --- perturbation observer --- vanadium redox flow battery --- genetic algorithm --- binary particle swarm optimization --- time-varying mirrored S-shaped transfer function --- greenhouse gas emissions --- heliostat --- sun tracking --- solar energy --- embedded system --- fuzzy logic control --- center of sums defuzzification method