Kinematics Design of a MacPherson Suspension Architecture Based on Bayesian Optimization

Thomas, Sinnu Susan; Palandri, Jacopo; Lakehal-Ayat, Mohsen; Chakravarty, Punarjay; Wolf‐Monheim, Friedrich; Blaschko, Matthew B.

doi:10.1109/tcyb.2021.3114403

Cited by 7 publications

(10 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many approaches where generative models are used [16]- [18] and are used when the search space is vast, data is not condensed in tabular arrays, and the computation of each point in the space is costly. The design also uses descriptive models in the literature [6,7]. GA needs to train the same model on multiple hyperparameters, whereas BO is used to train a single model, thus making it computationally efficient.…”

Section: Literature Reviewmentioning

confidence: 99%

“…This model resembles the actual distribution by a normal distribution. This work focuses on the Expected Improvement acquisition, Gaussian Process [6,7] and the ones used to optimize the KMM parameters.…”

Section: A Inverse Problem In Bomentioning

confidence: 99%

“…The data generated using the discipline models were uniformly random sampled, and those using Bayesian Optimization (BO) [6,7]. The algorithm's performance greatly depends on the data distributed in the search space.…”

Section: Introductionmentioning

confidence: 99%

“…The readers are encouraged to read our previous work [6,7] to get a broader perspective on the design of MacPherson architecture. The current paper aims to reuse the data generated by our previous work [6,7] using BO to train a learning algorithm that could provide exciting answers to the regression problem. If the dataset gives enough insight into the entire search space, the estimation function is as good as the BO but with no time delay.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Mitigating Bias in Bayesian Optimized Data While Designing MacPherson Suspension Architecture

Thomas,

Lamine,

Palandri

et al. 2024

IEEE Trans. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

With the rise of artificial intelligence, the automotive industry searched for novel ways to improve future product design. We focus on designing automatic MacPherson suspension architecture for the automotive sector. It takes time for an automotive engineer to design vehicle parts and thus slows the pace of innovation in this field. Given the car's particular kinematic characteristics, we propose to predict an architecture by positioning the hardpoints. This work deals with the biased data generated using the discipline models using the dataset shift learning paradigm. The optimized data are created with random and uniform sampling, with more samples with random sampling. We resolve the bias in the data, using a novel criterion for tuning the kernel mean matching and a weight estimation algorithm and designing the required target characteristics.Impact Statement-In the early stages of vehicle suspension design and development, decisions are generally made regarding suspension architecture within the constraints of a given packaging space, vehicle weight, and required travel. Kinematic characteristics are traditionally derived from a disciplined model. A disciplined model is a software program that studies the behavior of interconnected rigid and flexible mechanical components as they undergo translational and rotational displacements resulting from applied forces or motion as measured by displacement, velocity, and acceleration. We design the suspension based on the data produced using the disciplined models. This paper helps the community of automotive engineers to use artificial intelligence and make their design process fast.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: A Inverse Problem In Bomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Mitigating Bias in Bayesian Optimized Data While Designing MacPherson Suspension Architecture

Thomas,

Lamine,

Palandri

et al. 2024

IEEE Trans. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

“…V. BAYESIAN OPTIMIZATION BO [42] is a derivative free optimization approach for global optimization of expensive black-box function f . It is a class of sequential-model based optimization algorithms that uses past evaluations of the function to find the next point to sample.…”

Section: Controller Synthesismentioning

confidence: 99%

Generalized State-Feedback Controller Synthesis for Underactuated Systems through Bayesian Optimization

Solís¹,

Thomas²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Underactuated systems pose the challenge of being able to control a plant whose degrees of freedom are not necessarily directly linked to an actuator or where such a relationship is not straightforward. Rotary inverted pendulum is an example of such systems, which on its simplest representation consists of a pendulum whose vertical angle should be taken up to the upward unstable position based on the impulse given from another bar and an appropriate control strategy, bar that is controlled by an electrical motor. This problem is often tackled by linear control theory with state-feedback controllers that is frequently obtained by means of designing a feedback gain meeting some constraints. This article reports a Bayesian Optimization approach for designing a generalized state-feedback controller, that involves more parameters than a simple statefeedback control law, but with the benefit of achieving lower control effort in terms of the signal amplitude. The source code is made publicly available to facilitate further research.

show abstract

Alleviating Search Bias in Bayesian Evolutionary Optimization With Many Heterogeneous Objectives

Wang,

Jin,

Schmitt

et al. 2024

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

Kinematics Design of a MacPherson Suspension Architecture Based on Bayesian Optimization

Cited by 7 publications

References 36 publications

Mitigating Bias in Bayesian Optimized Data While Designing MacPherson Suspension Architecture

Mitigating Bias in Bayesian Optimized Data While Designing MacPherson Suspension Architecture

Generalized State-Feedback Controller Synthesis for Underactuated Systems through Bayesian Optimization

Alleviating Search Bias in Bayesian Evolutionary Optimization With Many Heterogeneous Objectives

Contact Info

Product

Resources

About