# A Neural Network-Based Real-time Casing Collar Recognition System for Downhole Instruments

arXiv: https://arxiv.org/abs/2512.22901 · HTML: https://mlsanity.com/paper/2512.22901/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 67 references that are in the map.
- First posted on arXiv 28 Dec 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [DropBlock: A regularization method for convolutional networks](https://mlsanity.com/paper/1810.12890/) (2018)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [Hello Edge: Keyword Spotting on Microcontrollers](https://mlsanity.com/paper/1711.07128/) (2017)
- [MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning](https://mlsanity.com/paper/2110.15352/) (2021)
- [Broadcasted Residual Learning for Efficient Keyword Spotting](https://mlsanity.com/paper/2106.04140/) (2021)
- [Dropout as data augmentation](https://mlsanity.com/paper/1506.08700/) (2015)
- [Realization of Precise Perforating Using Dynamic Threshold and Physical Plausibility Algorithm for Self-Locating Perforating in Oil and Gas Wells](https://mlsanity.com/paper/2509.00608/) (2025)
- [Data-Augmented Deep Learning for Downhole Depth Sensing and Validation](https://mlsanity.com/paper/2511.00129/) (2025)

## Abstract (arXiv)

Casing collar locator (CCL) measurements are widely used as reliable depth markers for positioning downhole instruments in cased-hole operations, enabling accurate depth control for operations such as perforation. However, autonomous collar recognition in downhole environments remains challenging because CCL signals are often corrupted by toolstring- or casing-induced magnetic interference, while stringent size and power budgets limit the use of computationally intensive algorithms and specific operations require real-time, in-situ processing. To address these constraints, we propose Collar Recognition Nets (CRNs), a family of domain-specific lightweight 1-D convolutional neural networks for collar signature recognition from streaming CCL waveforms. With depthwise separable convolutions and input pooling, CRNs optimize efficiency without sacrificing accuracy. Our most compact model achieves an F1-score of 0.972 on field data with only 1,985~parameters and 8,208~MACs, and deployed on an ARM Cortex-M7 based embedded system using TensorFlow Lite for Microcontrollers (TFLM) library, the model demonstrates a throughput of 1,000 inference per second and 343.2 μs latency, confirming the feasibility of robust, autonomous, and real-time collar recognition under stringent downhole constraints.