optimizing-human-powered-energy-generation-using-gaussian-process

Optimizing Human-Powered Energy Generation Using Gaussian Process Regression

This protocol presents a Gaussian Process Regression (GPR) optimization framework for human-powered electricity generation systems to address ...

Westlake University

Zhejiang Engineering Research Center of Micro/Nano-Photonic/Electronic System Integration

Nature-inspired computing has attracted huge attention since its origin, especially in the field of multiobjective optimization. This paper proposes a disruption-based multiobjective equilibrium optimization algorithm (DMOEOA). A novel mutation operator named layered disruption method is integrated into the proposed algorithm with the aim of enhancing the exploration and exploitation abilities of DMOEOA. To demonstrate the advantages of the proposed algorithm, various benchmarks have been selected with five different multiobjective optimization algorithms. The test results indicate that DMOEOA does exhibit better performances in these problems with a better balance between convergence and distribution. In addition, the new proposed algorithm is applied to the structural optimization of an elastic truss with the other five existing multiobjective optimization algorithms. The obtained results demonstrate that DMOEOA is not only an algorithm with good performance for benchmark problems but is also expected to have a wide application in real-world engineering optimization problems.

Disruption-Based Multiobjective Equilibrium Optimization Algorithm.

As the ocean development process speeds up, the technical means of ocean exploration are being upgraded. Due to the characteristics of seawater and the complex underwater environment, conventional measurement and sensing methods used for land are difficult to apply in the underwater environment directly. Especially for the seabed topography, it is impossible to carry out long-distance and accurate detection via electromagnetic waves. Therefore, various types of acoustic and even optical sensing devices for underwater applications have come into use. Equipped by submersibles, those underwater sensors can sense underwater wide-range and accurately. Moreover, the development of sensor technology will be modified and optimized according to the needs of ocean exploitation. This paper has made a summary of the ocean sensing technologies applied in some critical underwater scenarios, including geological surveys, navigation and communication, marine environmental parameters, and underwater inspections. In order to contain as many submersible-based sensors as possible, we have to make a trade-off on breadth and depth. In the end, the authors predict the development trend of underwater sensor technology based on the future ocean exploration requirements.

Review of Underwater Sensing Technologies and Applications.

The fast development of deep-ocean engineering equipment requires more deep-ocean pressure chambers (DOPCs) with a large inner diameter and ultra-high-pressure (UHP). Using the pre-stressed wire-wound (PSWW) concept, cold isostatic pressing (CIP) chambers have become a new concept of DOPCs, which can provide 100% performance of materials in theory. This paper aims to provide a comprehensive design process for a practical metal-made CIP chamber. First, the generalized design equations are derived by considering the fact that the cylinder and wire have different Young's moduli and Poisson's ratios. Second, to verify the theory and the reliability of the CIP chamber, the authors proposed a series of FEA models based on ANSYS Mechanical, including a two-dimensional (2D) model with the thermal strain method (TSM) and a three-dimensional (3D) model with the direct method (DM). The relative errors of the pre-stress coefficient range from 0.17% to 5%. Finally, the crack growth path is predicted by using ANSYS's Separating Morphing and Adaptive Remeshing Technology (SMART) algorithm, and the fatigue life is evaluated by using the unified fatigue life prediction (UFLP) method developed by the authors' group. This paper provides a more valuable basis to the design of DOPCs as well as to the similar pressure vessels than the previous work.

Design of a Practical Metal-Made Cold Isostatic Pressing (CIP) Chamber Using Finite Element Analysis.

Soft pneumatic actuators (SPAs) have attracted enormous attention in the growing field of robotics. Among different SPAs, composite reinforced actuators (CRAs) are widely used because of their simple structure and high controllability. However, multistep molding, a time-consuming method, is still the predominant fabrication method. Here, we propose a multimaterial embedded printing method (ME3P) to fabricate CRAs. In comparison with other 3-dimensional printing methods, our method improves fabrication flexibility greatly. Via the design and fabrication of the reinforced composites' patterns and different geometries of the soft body, we demonstrate actuators with programmable responses (elongation, contraction, twisting, bending, and helical and omnidirectional bending). Finite element analysis is employed for the prediction of pneumatic responses and the inverse design of actuators based on specific actuation needs. Lastly, we use tube-crawling robots as a model system to demonstrate our ability to fabricate complex soft robots for practical applications. This work demonstrates the versatility of ME3P for the future manufacturing of CRA-based soft robots.

Multimaterial Embedded 3D Printing of Composite Reinforced Soft Actuators.

We report self-organized periodic nanostructures on amorphous silicon thin films by femtosecond laser-induced oxidation. The dependence of structural periodicity on the thickness of silicon films and the substrate materials is investigated. The results reveal that when silicon film is 200 nm, the period of self-organized nanostructures is close to the laser wavelength and is insensitive to the substrates. In contrast, when the silicon film is 50 nm, the period of nanostructures is much shorter than the laser wavelength, and is dependent on the substrates. Furthermore, we demonstrate that, for the thick silicon films, quasi-cylindrical waves dominate the formation of periodic nanostructures, while for the thin silicon films, the formation originates from slab waveguide modes. Finite-difference time-domain method-based numerical simulations support the experimental discoveries.

Impact of film thickness in laser-induced periodic structures on amorphous Si films.

Bionic robotics, driven by advancements in artificial intelligence, new materials, and manufacturing technologies, is attracting significant attention from research and industry communities seeking breakthroughs. One of the key technologies for achieving a breakthrough in robotics is flexible sensors. This paper presents a novel approach based on wavelength and time division multiplexing (WTDM) for distributed optical waveguide shape sensing. Structurally designed optical waveguides based on color filter blocks validate the proposed approach through a cost-effective experimental setup. During data collection, it combines optical waveguide transmission loss and the way of controlling the color and intensity of the light source and detecting color and intensity variations for modeling. An artificial neural network is employed to model and demodulate a data-driven optical waveguide shape sensor. As a result, the correlation coefficient between the predicted and real bending angles reaches 0.9134 within 100 s. To show the parsing performance of the model more intuitively, a confidence accuracy curve is introduced to describe the accuracy of the data-driven model at last.

Low-Cost Distributed Optical Waveguide Shape Sensor Based on WTDM Applied in Bionics.

Because of their many excellent properties, hollow glass beads (HGBs) are widely used in composite materials; stealth coatings; the aerospace field; the deep-sea field; electrical, thermal and sound insulation materials and military explosives. However, there is currently no method for predicting the strength of HGBs. This paper proposes a probability distribution model for the compressive strength of micro thin-walled HGBs under uniform pressure. The theoretical model was verified by comparing the parameters of 13 types of HGBs. The model showed that compressive strength is inversely proportional to the square root of the radius for the same type of HGBs. Moreover, for different types of HGBs made with identical materials, the compressive strength is only related to the outer diameter and equivalent density. Further study revealed that the particle size of HGBs follows a normal distribution. The failure mode of HGBs under uniform pressure is mode-II. Therefore, the maximum shear stress, which occurs on the inner surface of HGBs, is the dominant factor in the failure process. Furthermore, the shear strength is only inversely proportional to the square root of the radius even for different types of HGBs.

A probability distribution model for the compressive strength of micro thin-walled hollow glass beads under uniform pressure.

We develop a multitask and multifidelity Gaussian process (MMGP) model to accurately predict and optimize the multiobjective performance of a flapping foil while minimizing the cost of high-fidelity data. Through a comparison of three kernels, we have selected and applied the spectral mixture kernel and validated the robustness and effectiveness of a multiacquisition function. To effectively incorporate data with varying levels of fidelity, we have adopted a linear prior formula-based multifidelity framework. Additionally, Bayesian optimization with a multiacquisition function is adopted by the MMGP model to enable multitask active learning. The results unequivocally demonstrate that the MMGP model serves as a highly capable and efficient framework for effectively addressing the multiobjective challenges associated with flapping foils.

Multiobjective optimization for flapping foil hydrodynamics with a multitask and multifidelity approach.

The miniaturization of ocean parameter monitors is critical for environmental monitoring and oceanographic research. In recent years, rapid developments in data processing, artificial intelligence, micro-nano manufacturing and advanced materials have significantly improved sensing accuracy while reducing device size. The detection of key ocean parameters such as temperature, salinity, pressure, dissolved oxygen (DO), pH, nutrients, chlorophyll and so on is facilitated by these innovations. Among these emerging technologies, microfluidics and optofluidics have attracted large attention in the fields of biomedicine and environmental monitoring. These platforms have the advantages of high sensitivity, low power consumption and easy integration. Real-time and on-site monitoring can be achieved by them. Optofluidic technology shows great prospects for ocean sensing applications. Recent advances in optofluidic ocean sensors for the measurement of chemical parameters and their future potential are highlighted in this review. Ultimately, it presents the key role of optofluidic systems in realizing compact high-performance ocean parameter sensors. This plays an important role in paving the way for their integration into micro robots and the fourth generation of submersibles based on live fish.

Article	Year
Disruption-Based Multiobjective Equilibrium Optimization Algorithm. Computational intelligence and neuroscience\| PubMed ID: 33335543	2020
Review of Underwater Sensing Technologies and Applications. Sensors (Basel, Switzerland)\| PubMed ID: 34883851	2021
Design of a Practical Metal-Made Cold Isostatic Pressing (CIP) Chamber Using Finite Element Analysis. Materials (Basel, Switzerland)\| PubMed ID: 35629648	2022
Multimaterial Embedded 3D Printing of Composite Reinforced Soft Actuators. Research (Washington, D.C.)\| PubMed ID: 37223483	2023
Impact of film thickness in laser-induced periodic structures on amorphous Si films. Frontiers of optoelectronics\| PubMed ID: 37338710	2023
Low-Cost Distributed Optical Waveguide Shape Sensor Based on WTDM Applied in Bionics. Sensors (Basel, Switzerland)\| PubMed ID: 37687790	2023
A probability distribution model for the compressive strength of micro thin-walled hollow glass beads under uniform pressure. Heliyon\| PubMed ID: 38053858	2023
Multiobjective optimization for flapping foil hydrodynamics with a multitask and multifidelity approach. Physical review. E\| PubMed ID: 38366476	2024
Miniaturization of Ocean Sensors Based on Optofluidic Technology: A Review. Sensors (Basel, Switzerland)\| PubMed ID: 41228814	2025

Weicheng Cui

Biography

JoVE Journal Publications

Other Publications