Evolutionary hardware-in-the-loop optimization of a controller for cascaded hydraulic valves

Krettek, Johannes; Schauten, Daniel; Hoffmann, Frank; Bertram, Torsten

doi:10.1109/aim.2007.4412540

Cited by 12 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Further researches were conducted to optimize the design parameters for a two-stage, 2-way hydraulic valve for water hydraulics [124] and for construction machinery applications [125]. Another was performed to optimize the controller of the Pilot valve alongside the main valve [126]. For pressure control Pilot operated valves, it can be seen in shift control for automatic transmission [127], and in investigating a pressure regulator for vehicle suspension [128].…”

Section: Pressure Control Units In Heavy Duty Automatic Transmissionmentioning

confidence: 99%

A Review of Pilot-operated Hydraulic Valves – Development, Challenges, and a Comparative Study

Elsaed,

Linjama

2023

TJFP

View full text Add to dashboard Cite

Hydraulic systems have been widely used due to their high power-to-weight ratio. Despite the growing instances of being superseded by the electromechanical counterparts at low power levels, the market was incapable of presenting alternatives for large-size applications. Additionally, in recent years, the demand for more significant heavy machinery (Mobile & Industrial) has increased, which led to the necessity of even higher flow and pressure Pilot-operated valves, despite the fact that these valves have several issues. One might think the alternative could be developing a hydraulic system that does not rely on Pilot-operated valves, but after decades of research, these systems could not get close to the performance of Pilot-operated Multistage valves. The paper presents a comprehensive study of the progress accomplished from the year 2016 to early 2022 in hydraulic Pilot-operated valves; they are widely employed among ordinary valves, proportional valves, and state-of-the-art digital hydraulics. Higher efficiency will be a primary factor in the success of the new designs. The academia presented several studies to improve the Pilot valves’ performance, but still, they are limited. There are no dramatic developments, and there are only a few upgrades.

show abstract

Section: Pressure Control Units In Heavy Duty Automatic Transmissionmentioning

confidence: 99%

A Review of Pilot-operated Hydraulic Valves – Development, Challenges, and a Comparative Study

Elsaed,

Linjama

2023

TJFP

View full text Add to dashboard Cite

show abstract

“…In evolutionary hardware-in-the-loop optimization of control systems, such as Krettek et al (2007), a single fitness evaluation takes several seconds. Obviously, extensive evaluations, simulations, or calculations of the fitness function constrain the feasible population size and number of generations in the evolutionary optimization of technical systems.…”

Section: Introductionmentioning

confidence: 99%

Multi-Objective Optimization with Controlled Model Assisted Evolution Strategies

Braun

Krettek

Hoffmann

et al. 2009

Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

Evolutionary algorithms perform robust search in complex and high dimensional search spaces, but require a large number of fitness evaluations to approximate optimal solutions. These characteristics limit their potential for hardware in the loop optimization and problems that require extensive simulations and calculations. Evolutionary algorithms do not maintain their knowledge about the fitness function as they only store solutions of the current generation. In contrast, model assisted evolutionary algorithms utilize the information contained in previously evaluated solutions in terms of a data based model. The convergence of the evolutionary algorithm is improved as some selection decisions rely on the model rather than to invoke expensive evaluations of the true fitness function. The novelty of our scheme stems from the preselection of solutions based on an instance based fitness model, in which the selection pressure is adjusted to the quality of model. This so-called λ-control adapts the number of true fitness evaluations to the monitored model quality. Our method extends the previous approaches for model assisted scalar optimization to multi-objective problems by a proper redefinition of model quality and preselection pressure control. The analysis on multi-objective benchmark optimization problems not only confirms the superior convergence of the model assisted evolution strategy in comparison with a multi-objective evolution strategy but also the positive effect of regulated preselection in contrast to merely static preselection.

show abstract

“…Bei der evolutionären Hardware-inthe-Loop Optimierung von Regelungssystemen [1] benö-tigt eine einzige Gütebewertung unter Umständen mehrere Sekunden. Offenkundig schränkt dieser Zeitaufwand die praktische Anwendbarkeit von evolutionären Algorithmen bezüglich der Größe der Population und der GenerationenAnzahl bei der Optimierung technischer Systeme ein.…”

Section: Introductionunclassified

Multikriterielle Optimierung mit λ-geregelten modellgestützten EvolutionsstrategienModel Assisted Multiobjective Optimization with λ-Control

Braun¹,

Hoffmann

Krettek

et al. 2009

At - Automatisierungstechnik

Self Cite

View full text Add to dashboard Cite

Evolutionäre Algorithmen benötigen für die Optimierung eine hohe Anzahl an Auswertungen der Gütefunktion. Dieser Aufwand limitiert ihre Anwendbarkeit bei der Hardware-in-theLoop Optimierung und bei auf zeitaufwändigen Simulationen und Berechnungen basierenden Optimierungsaufgaben. Dieser Beitrag präsentiert einen neuartigen Ansatz zur Fitnessmodellierung, welcher die Anzahl an Güteauswertungen mit Hilfe einer Vorselektion deutlich reduziert. Die Innovation des Ansatzes besteht in der gezielten Regelung des Selektionsdrucks innerhalb der Vorselektion anhand der geschätzten Modellgüte. Diese sogenannte λ-Regelung garantiert gegenüber einer rein statischen Vorselektion eine effiziente Optimierung bezüglich der benötigten Güteauswertungen. Zudem erweitert die hier vorgestellte Methode die bekannten Ansätze zur modellgestützten, skalaren, evolutionären Optimierung auf multikriterielle Probleme. Die Optimierungsergebnisse an Benchmarkproblemen weisen eine verbesserte Konvergenz gegenüber herkömmlichen multikriteriellen Evolutionsstrategien auf und belegen die Effizienz der λ-geregelten Variante.Evolutionary algorithms require a large number of fitness evaluations in order to find an optimal solution. This property limits their application to hardware in the loop optimization or optimization of time-consuming simulations and calculations. This contribution proposes a preselection with data based models in order to reduce the number of true fitness evaluations. It extends previous approaches for model assisted scalar optimization to multiobjective problems by a proper redefinition of model quality and λ-control. The application to multiobjective benchmark optimization problems underlies the improved convergence of the model assisted evolution strategy compared to a multiobjective evolution strategy as well as the advantages of a λ-controlled variant compared to a static preselection.Schlagwörter: Multikriterielle Optimierung, Fitnessmodellierung, evolutionäre Algorithmen

show abstract

Evolutionary hardware-in-the-loop optimization of a controller for cascaded hydraulic valves

Cited by 12 publications

References 6 publications

A Review of Pilot-operated Hydraulic Valves – Development, Challenges, and a Comparative Study

A Review of Pilot-operated Hydraulic Valves – Development, Challenges, and a Comparative Study

Multi-Objective Optimization with Controlled Model Assisted Evolution Strategies

Multikriterielle Optimierung mit λ-geregelten modellgestützten EvolutionsstrategienModel Assisted Multiobjective Optimization with λ-Control

Contact Info

Product

Resources

About