A 280-Parameter Embedding-Constrained Network for Autonomous Rate-of-Penetration Optimization on a Microcontroller
Open Access
- 22 October 2026
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (21) , 10465
Abstract
Rate of penetration (ROP) prediction is essential for drilling efficiency, yet prevailing deep learning models employ millions of parameters and rely on surface-based pipelines constrained by low-bandwidth telemetry and round-trip delays measured in minutes to hours. These delays make surface-computed optimization decisions obsolete before they reach the bit, leaving real-time drilling intelligence infeasible. We present ROP MCU_model, an encoder–regressor neural network with only 280 trainable parameters that performs autonomous ROP prediction and optimization entirely on a microcontroller. Discovered through genetic-algorithm neural architecture search and trained with supervised contrastive learning, the model imposes structural constraints on the latent embedding space to maintain accuracy under extreme parameter scarcity. Full-integer quantization compresses the network to 5.57 KB, enabling inference in 156 μs on an ESP32-S3 via TensorFlow Lite Micro. An integrated on-device optimization engine searches controllable drilling parameters within a bounded search envelope without surface communication. Validated under leave-two-well-out cross-validation on field data from the Taranaki Basin, the model achieves a mean weighted mean absolute percentage error (WMAPE) of 0.687 over nine seeded evaluation splits, the lowest prediction error among all competing models. Recomputing all normalization bounds from training-stage wells only reproduces this result within 0.2%, indicating no split-dependent leakage and a negligible effect. The on-device optimizer delivers a mean surrogate-model-predicted ROP improvement of 46.2% (median 18.5%). This work demonstrates closure of the sense–predict–optimize–decide decision loop on a commodity microcontroller; transferring the methodology to other telemetry-constrained downhole tasks remains future work.Keywords
Funding Information
- Institute of Geology and Geophysics, Chinese Academy of Sciences (E5555801)
- National Natural Science Foundation of China (42102351)
This publication has 28 references indexed in Scilit:
- Real-time discrimination of earthquake signals by integrating artificial intelligence technology into IoT devicesCommunications Earth & Environment, 2025
- ROP Prediction Method Based on PCA–Informer ModelingACS Omega, 2024
- Hybrid physics-machine learning models for predicting rate of penetration in the Halahatang oil field, Tarim BasinScientific Reports, 2024
- Real-time prediction of rate of penetration by combining attention-based gated recurrent unit network and fully connected neural networksJournal of Petroleum Science and Engineering, 2022
- Reference dataset for rate of penetration benchmarkingJournal of Petroleum Science and Engineering, 2021
- Is Support Vector Regression method suitable for predicting rate of penetration?Journal of Petroleum Science and Engineering, 2020
- Machine learning methods applied to drilling rate of penetration prediction and optimization - A reviewJournal of Petroleum Science and Engineering, 2019
- Computational intelligence based prediction of drilling rate of penetration: A comparative studyJournal of Petroleum Science and Engineering, 2019
- Real-time predictive capabilities of analytical and machine learning rate of penetration (ROP) modelsJournal of Petroleum Science and Engineering, 2019
- Analysis of rate of penetration (ROP) prediction in drilling using physics-based and data-driven modelsJournal of Petroleum Science and Engineering, 2017