A machine learning-guided design and manufacturing of wearable nanofibrous acoustic energy harvesters
Bibliographic record
Abstract
Nanofibrous acoustic energy harvesters (NAEHs) have emerged as promising wearable platforms for efficient noise-to-electricity conversion in distributed power energy systems and wearable sound amplifiers for assistive listening devices. However, their real-life efficacy is hampered by low power output, particularly in the low-frequency range (< 1 kHz). This study introduces a novel approach to enhance the performance of NAEHs by applying machine learning (ML) techniques to guide the synthesis of electrospun polyvinylidene fluoride (PVDF)/polyurethane (PU) nanofibers, optimizing their application in wearable NAEHs. We use a feed-forward neural network along with solving an optimization problem to find the optimal input values of the electrospinning (applied voltage, nozzle-collector distance, electrospinning time, and drum rotation speed) to generate maximum output performance (acoustic-to-electricity conversion efficiency). We first prepared a dataset to train the network to predict the output power given the input variables with high accuracy. Upon introducing the neural network, we fix the network and then solve an optimization problem using a genetic algorithm to search for the input values that lead to the maximum energy harvesting efficiency. Our ML-guided wearable PVDF/PU NAEH platform can deliver a maximal acoustoelectric power density output of 829 µW/cm3 within the surrounding noise levels. In addition, our system can function stably in a broad frequency (0.1–2 kHz) with a high energy conversion efficiency of 66%. Sound recognition analysis reveals a robust correlation exceeding 0.85 among lexically akin terms with varying sound intensities, contrasting with a diminished correlation below 0.27 for words with disparate semantic connotations. Overall, this work provides a previously unexplored route to utilize ML in advancing wearable NAEHs with excellent practicability.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".