Vortex-induced vibration wind energy harvesting by piezoelectric MEMS device in formation

Lee, Yin Jen; Qi, Yi; Zhou, Guangya; Lua, Kim Boon

doi:10.1038/s41598-019-56786-0

Cited by 54 publications

(26 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar problem occurs with reinforcement learning (RL), where a learned policy without introduction of randomness always leads to one and only one molecule (policy collapse). Beyond the addition of randomness, several RL-based generators included other mechanisms to increase diversity [ 21 – 23 ]. These solutions are quite specific to the proposed generator or to the generation method.…”

Section: Introductionmentioning

confidence: 99%

Scalable estimator of the diversity for de novo molecular generation resulting in a more robust QM dataset (OD9) and a more efficient molecular optimization

2021

View full text Add to dashboard Cite

Chemical diversity is one of the key term when dealing with machine learning and molecular generation. This is particularly true for quantum chemical datasets. The composition of which should be done meticulously since the calculation is highly time demanding. Previously we have seen that the most known quantum chemical dataset QM9 lacks chemical diversity. As a consequence, ML models trained on QM9 showed generalizability shortcomings. In this paper we would like to present (i) a fast and generic method to evaluate chemical diversity, (ii) a new quantum chemical dataset of 435k molecules, OD9, that includes QM9 and new molecules generated with a diversity objective, (iii) an analysis of the diversity impact on unconstrained and goal-directed molecular generation on the example of QED optimization. Our innovative approach makes it possible to individually estimate the impact of a solution to the diversity of a set, allowing for effective incremental evaluation. In the first application, we will see how the diversity constraint allows us to generate more than a million of molecules that would efficiently complete the reference datasets. The compounds were calculated with DFT thanks to a collaborative effort through the QuChemPedIA@home BOINC project. With regard to goal-directed molecular generation, getting a high QED score is not complicated, but adding a little diversity can cut the number of calls to the evaluation function by a factor of ten

show abstract

Section: Introductionmentioning

confidence: 99%

Scalable estimator of the diversity for de novo molecular generation resulting in a more robust QM dataset (OD9) and a more efficient molecular optimization

2021

View full text Add to dashboard Cite

show abstract

“…Energies 2020, 13, x FOR PEER REVIEW 2 of 15 reviewed [18,19] in several applications. The vortex-induced vibration method is a common practice used to harvest the kinetic energy of a fluid using piezoelectric transducers [20]. This work reports the comprehensive evaluation of the energy available and harvestable in exhaust gas in different forms, such as thermal, pressure and kinetic, at different positions of the exhaust system, and at different engine operating conditions (engine speed and torque).…”

Section: Thoretical Model For Evaluating Exhaust Gas Energymentioning

confidence: 99%

Available Energy in Cars’ Exhaust System for IoT Remote Exhaust Gas Sensor and Piezoelectric Harvesting

et al. 2020

View full text Add to dashboard Cite

The exhaust system of the light-duty diesel engine has been evaluated as a potential environment for a mechanical energy recovery system for powering an IoT (Internet of Things) remote sensor. Temperature, pressure, gas speed, mass flow rate have been measured in order to characterize the exhaust gas. At any engine point explored, thermal energy is by far the most dominant portion of the exhaust energy, followed by the pressure energy and lastly kinetic energy is the smallest fraction of the exhaust energy. A piezoelectric flexible device has been tested as a possible candidate as an energy harvester converting the kinetic energy of the exhaust gas flow, with a promising amount of electrical energy generated in the order of microjoules for an urban or extra-urban circuit.

show abstract

“…Other RL methods such as Deep Q-Learning are also proven to be a successful way of research. Zhou et al designed new molecules with specific desired properties, formalizing the problem as a Markov Decision Process (MDP) and using a value function to solve [ 12 ].…”

Section: Introductionmentioning

confidence: 99%

Diversity oriented Deep Reinforcement Learning for targeted molecule generation

et al. 2021

View full text Add to dashboard Cite

In this work, we explore the potential of deep learning to streamline the process of identifying new potential drugs through the computational generation of molecules with interesting biological properties. Two deep neural networks compose our targeted generation framework: the Generator, which is trained to learn the building rules of valid molecules employing SMILES strings notation, and the Predictor which evaluates the newly generated compounds by predicting their affinity for the desired target. Then, the Generator is optimized through Reinforcement Learning to produce molecules with bespoken properties. The innovation of this approach is the exploratory strategy applied during the reinforcement training process that seeks to add novelty to the generated compounds. This training strategy employs two Generators interchangeably to sample new SMILES: the initially trained model that will remain fixed and a copy of the previous one that will be updated during the training to uncover the most promising molecules. The evolution of the reward assigned by the Predictor determines how often each one is employed to select the next token of the molecule. This strategy establishes a compromise between the need to acquire more information about the chemical space and the need to sample new molecules, with the experience gained so far. To demonstrate the effectiveness of the method, the Generator is trained to design molecules with an optimized coefficient of partition and also high inhibitory power against the Adenosine $$A_{2A}$$ A 2 A and $$\kappa$$ κ opioid receptors. The results reveal that the model can effectively adjust the newly generated molecules towards the wanted direction. More importantly, it was possible to find promising sets of unique and diverse molecules, which was the main purpose of the newly implemented strategy.

show abstract

Vortex-induced vibration wind energy harvesting by piezoelectric MEMS device in formation

Cited by 54 publications

References 15 publications

Scalable estimator of the diversity for de novo molecular generation resulting in a more robust QM dataset (OD9) and a more efficient molecular optimization

Scalable estimator of the diversity for de novo molecular generation resulting in a more robust QM dataset (OD9) and a more efficient molecular optimization

Available Energy in Cars’ Exhaust System for IoT Remote Exhaust Gas Sensor and Piezoelectric Harvesting

Diversity oriented Deep Reinforcement Learning for targeted molecule generation

Contact Info

Product

Resources

About