From MCU to Neuromorphic Chip: A Zero-Gradient Spiking-Compatible Engine for Cross-Domain Predictive Maintenance
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Real-time predictive maintenance on resource-constrained edge hardware demands sub-millisecond inference, online adaptation without retraining, and reliable generalization across heterogeneous industrial domains. We present a zero-gradient neural dynamics engine: a population of computational units governed entirely by local plasticity rules, discrete population-level gating, and resource-constrained structural adaptation. The frozen model occupies 50–100 KB with no GPU dependency. We evaluate nine task configurations across five physical datasets (bearing fault diagnosis on CWRU and Paderborn, satellite telemetry anomaly detection on SMAP, bridge structural health monitoring on Z24, audio machine monitoring on DCASE, human activity recognition on UCI HAR, and cross-domain transfer), plus one real-world tunnel construction monitoring deployment, using a single unmodified engine configuration. The engine achieves a mean improvement of +22.6 percentage points over raw-feature baselines across all nine configurations; on the four bearing fault tasks, multi-seed consensus voting further pushes accuracy to ≥99.9%. End-to-end inference latency is 53 µs on x86, 103 µs on ARM (Raspberry Pi 5), and∼350 µs on a Cortex-M7 MCU at 600 MHz. All engine primitives operate without surrogate gradients or backpropagation, and exact SNN mapping to a neuromorphic chip has been verified. Engine routing is fully unsupervised: online k-means discovers K regimes from the input stream without consuming labels. A one-time calibration step of 50–200 labeled samples, supplied either by a domain expert or by a cloud-based LLM oracle, then maps these discovered regimes to domain-specific fault categories; thereafter the engine runs autonomously.
How to Cite
##plugins.themes.bootstrap3.article.details##
Predictive Maintenance, Spiking Neural Networks, Neuromorphic Computing, Zero-Gradient Learning, Edge AI, Cross-Domain Generalization, Structural Health Monitoring, Bearing Fault Diagnosis, Online Unsupervised Learning, Anomaly Detection
Bi, G.-Q., & Poo, M.-M. (1998). Synaptic modifications in cultured hippocampal neurons: Dependence on spike timing, synaptic strength, and postsynaptic cell type. Journal of Neuroscience, 18(24), 10464–10472.
Bouhadjar, Y., Wouters, D. J., Diesmann, M., & Tetzlaff, T. (2022). Sequence learning, prediction, and replay in networks of spiking neurons. PLoS Computational Biology, 18(6), e1010233.
Davies, M., Wild, A., Orber, G., et al. (2021). Advancing neuromorphic computing with Loihi: A survey of results and outlook. Proceedings of the IEEE, 109(5), 911–934.
Diehl, P. U., & Cook, M. (2015). Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Frontiers in Computational Neuroscience, 9, 99.
Hundman, K., Constantinou, V., Laporte, C., Colwell, I., & Soderstrom, T. (2018). Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 387–395).
Indiveri, G., et al. (2011). Neuromorphic silicon neuron circuits. Frontiers in Neuroscience, 5, 73.
Innatera Nanosystems. (2025). Pulsar: The world’s first mass-market neuromorphic microcontroller for the sensor edge [Product datasheet]. Retrieved from https://innatera.com/pulsar
Jacobs, R. A., Jordan, M. I., Nowlan, S. J., & Hinton, G. E. (1991). Adaptive mixtures of local experts. Neural Computation, 3(1), 79–87.
Khan, S., & Yairi, T. (2018). A review on the application of deep learning in system health management. Mechanical Systems and Signal Processing, 107, 241–265.
Koizumi, Y., et al. (2020). Description and discussion on DCASE 2020 Challenge Task 2. In Proceedings of the DCASE Workshop (pp. 1–5).
Lansner, A. (2009). Associative memory models: From the cell-assembly theory to biophysically detailed cortex simulations. Trends in Neurosciences, 32(3), 178–186.
Lei, Y., Yang, B., Jiang, X., Jia, F., Li, N., & Nandi, A. K. (2020). Applications of machine learning to machine fault diagnosis: A review and roadmap. Mechanical Systems and Signal Processing, 138, 106587.
Lessmeier, C., Kimotho, J. K., Zimmer, D., & Sextro, W. (2016). Condition monitoring of bearing damage in electromechanical drive systems. In Proceedings of the European Conference of the PHM Society. Bilbao, Spain.
Maass, W. (2000). On the computational power of winner-take-all. Neural Computation, 12(11), 2519–2535.
Maass, W., Natschläger, T., & Markram, H. (2002). Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation, 14(11), 2531–2560.
Maeck, J., & De Roeck, G. (2003). Description of Z24 benchmark. Mechanical Systems and Signal Processing, 17(1), 127–131.
Mozafari, M., Ganjtabesh, M., Nowzari-Dalini, A., Thorpe, S. J., & Masquelier, T. (2019). Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks. Pattern Recognition, 94, 87–95.
Neftci, E. O., Mostafa, H., & Zenke, F. (2019). Surrogate gradient learning in spiking neural networks. IEEE Signal Processing Magazine, 36(6), 51–63.
Rumelhart, D. E., & Zipser, D. (1985). Feature discovery by competitive learning. Cognitive Science, 9(1), 75–112.
Scellier, B., & Bengio, Y. (2017). Equilibrium propagation: Bridging the gap between energy-based models and backpropagation. Frontiers in Computational Neuroscience, 11, 24.
Schuman, C. D., Kulkarni, S. R., Parsa, M., Mitchell, J. P., Date, P., & Kay, B. (2022). Opportunities for neuromorphic computing algorithms and applications. Nature Computational Science, 2, 10–19.
Smith, W. A., & Randall, R. B. (2015). Rolling element bearing diagnostics using the Case Western Reserve University data. Mechanical Systems and Signal Processing, 64–65, 100–131.
Tanaka, G., et al. (2019). Recent advances in physical reservoir computing: A review. Neural Networks, 115, 100–123.
Tully, P. J., Hennig, M. H., & Lansner, A. (2014). Synaptic and nonsynaptic plasticity approximating probabilistic inference. Frontiers in Synaptic Neuroscience, 6, 8.
Turrigiano, G. G. (2008). The self-tuning neuron: Synaptic scaling of excitatory synapses. Cell, 135(3), 422–435.
Turrigiano, G. G., & Nelson, S. B. (2004). Homeostatic plasticity in the developing nervous system. Nature Reviews Neuroscience, 5, 97–107.
Verstraeten, D., Schrauwen, B., D’Haene, M., & Stroobandt, D. (2007). An experimental unification of reservoir computing methods. Neural Networks, 20(3), 391–403.
Whittington, J. C. R., & Bogacz, R. (2017). An approximation of the error backpropagation algorithm in a predictive coding network with local Hebbian synaptic plasticity. Neural Computation, 29(5), 1229–1262.
Yamazaki, K., Vo-Ho, V.-K., Bulsara, D., & Le, N. (2022). Spiking neural networks and their applications: A review. Brain Sciences, 12(7), 863.
Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P., & Gao, R. X. (2019). Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing, 115, 213–237.
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.