# Neuroscience-Inspired Algorithms for the Predictive Maintenance of Manufacturing Systems

arXiv: https://arxiv.org/abs/2102.11450 · HTML: https://mlsanity.com/paper/2102.11450/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 41 references that are in the map.
- First posted on arXiv 23 Feb 2021.

## Builds on (most cited first, 3 of 3)

- [Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortex](https://mlsanity.com/paper/1511.00083/) (2015)
- [Conformalized density- and distance-based anomaly detection in time-series data](https://mlsanity.com/paper/1608.04585/) (2016)
- [Expected Similarity Estimation for Large-Scale Batch and Streaming Anomaly Detection](https://mlsanity.com/paper/1601.06602/) (2016)

## Built on by (most cited first, 2 of 2)

- [Meta-Learning Based Early Fault Detection for Rolling Bearings via Few-Shot Anomaly Detection](https://mlsanity.com/paper/2204.12637/) (2022)
- [Low-Power, Neuromorphic, Acoustic Anomaly Detection for Persistent Machine Monitoring](https://mlsanity.com/paper/2608.18341/) (2026)

## Abstract (arXiv)

If machine failures can be detected preemptively, then maintenance and repairs can be performed more efficiently, reducing production costs. Many machine learning techniques for performing early failure detection using vibration data have been proposed; however, these methods are often power and data-hungry, susceptible to noise, and require large amounts of data preprocessing. Also, training is usually only performed once before inference, so they do not learn and adapt as the machine ages. Thus, we propose a method of performing online, real-time anomaly detection for predictive maintenance using Hierarchical Temporal Memory (HTM). Inspired by the human neocortex, HTMs learn and adapt continuously and are robust to noise. Using the Numenta Anomaly Benchmark, we empirically demonstrate that our approach outperforms state-of-the-art algorithms at preemptively detecting real-world cases of bearing failures and simulated 3D printer failures. Our approach achieves an average score of 64.71, surpassing state-of-the-art deep-learning (49.38) and statistical (61.06) methods.