{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T19:13:56Z","timestamp":1780859636360,"version":"3.54.1"},"reference-count":61,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T00:00:00Z","timestamp":1719273600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"School of Electronic Engineering, North China University of Water Resources and Electric Power"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The South-to-North Water Diversion Project in China is an extensive inter-basin water transfer project, for which ensuring the safe operation and maintenance of infrastructure poses a fundamental challenge. In this context, structural health monitoring is crucial for the safe and efficient operation of hydraulic infrastructure. Currently, most health monitoring systems for hydraulic infrastructure rely on commercial software or algorithms that only run on desktop computers. This study developed for the first time a lightweight convolutional neural network (CNN) model specifically for early detection of structural damage in water supply canals and deployed it as a tiny machine learning (TinyML) application on a low-power microcontroller unit (MCU). The model uses damage images of the supply canals that we collected as input and the damage types as output. With data augmentation techniques to enhance the training dataset, the deployed model is only 7.57 KB in size and demonstrates an accuracy of 94.17 \u00b1 1.67% and a precision of 94.47 \u00b1 1.46%, outperforming other commonly used CNN models in terms of performance and energy efficiency. Moreover, each inference consumes only 5610.18 \u03bcJ of energy, allowing a standard 225 mAh button cell to run continuously for nearly 11 years and perform approximately 4,945,055 inferences. This research not only confirms the feasibility of deploying real-time supply canal surface condition monitoring on low-power, resource-constrained devices but also provides practical technical solutions for improving infrastructure security.<\/jats:p>","DOI":"10.3390\/s24134124","type":"journal-article","created":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T09:29:33Z","timestamp":1719394173000},"page":"4124","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Tiny-Machine-Learning-Based Supply Canal Surface Condition Monitoring"],"prefix":"10.3390","volume":"24","author":[{"given":"Chengjie","family":"Huang","sequence":"first","affiliation":[{"name":"School of Electronic Engineering, North China University of Water Resources and Electric Power, Jinshui East Road No. 136, Zhengzhou 450046, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinjuan","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, North China University of Water Resources and Electric Power, Jinshui East Road No. 136, Zhengzhou 450046, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8617-0435","authenticated-orcid":false,"given":"Yuxuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer and Electrical Engineering, Mid Sweden University, 85170 Sundsvall, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,6,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1111\/j.1752-1688.2009.00357.x","article-title":"The South-to-North Water Transfer Project of China: Environmental Implications and Monitoring Strategy 1","volume":"45","author":"Zhang","year":"2009","journal-title":"JAWRA J. Am. Water Resour. Assoc."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3665","DOI":"10.1038\/s41467-020-17428-6","article-title":"South-to-North Water Diversion stabilizing Beijing\u2019s groundwater levels","volume":"11","author":"Long","year":"2020","journal-title":"Nat. Commun."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.eng.2023.05.012","article-title":"A Review of the Eco-Environmental Impacts of the South-to-North Water Diversion: Implications for Interbasin Water Transfers","volume":"30","author":"Yan","year":"2023","journal-title":"Engineering"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"4063","DOI":"10.1007\/s11269-017-1728-0","article-title":"Methodology for establishing risk criteria for dams in developing countries, case study of China","volume":"31","author":"Ge","year":"2017","journal-title":"Water Resour. Manag."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1111\/mice.12334","article-title":"Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types","volume":"33","author":"Cha","year":"2018","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1007\/s00366-021-01584-4","article-title":"A framework of structural damage detection for civil structures using a combined multi-scale convolutional neural network and echo state network","volume":"39","author":"He","year":"2023","journal-title":"Eng. Comput."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"111543","DOI":"10.1016\/j.measurement.2022.111543","article-title":"Fibre-optic sensor and deep learning-based structural health monitoring systems for civil structures: A review","volume":"199","author":"Jayawickrema","year":"2022","journal-title":"Measurement"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"103200","DOI":"10.1016\/j.autcon.2020.103200","article-title":"UAV payload with collision mitigation for contact inspection","volume":"115","author":"Arias","year":"2020","journal-title":"Autom. Constr."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1495","DOI":"10.1007\/s00521-016-2666-0","article-title":"A novel hybrid artificial intelligent approach based on neural fuzzy inference model and particle swarm optimization for horizontal displacement modeling of hydropower dam","volume":"29","author":"Bui","year":"2018","journal-title":"Neural Comput. Appl."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"194228","DOI":"10.1109\/ACCESS.2020.3033289","article-title":"A deep learning-based hybrid framework for object detection and recognition in autonomous driving","volume":"8","author":"Li","year":"2020","journal-title":"IEEE Access"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"107077","DOI":"10.1016\/j.ymssp.2020.107077","article-title":"A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications","volume":"147","author":"Avci","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_12","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"106918","DOI":"10.1016\/j.compstruc.2022.106918","article-title":"Convolutional networks and transformers for intelligent road tunnel investigations","volume":"275","author":"Rosso","year":"2023","journal-title":"Comput. Struct."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1177\/14759217231193102","article-title":"Damage identification using convolutional neural networks from instantaneous displacement measurements via image processing","volume":"23","author":"Resende","year":"2024","journal-title":"Struct. Health Monit."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Bader, S., and Oelmann, B. (2022, January 1\u20133). A Lightweight Convolutional Neural Network Model for Concrete Damage Classification using Acoustic Emissions. Proceedings of the 2022 IEEE Sensors Applications Symposium (SAS), Sundsvall, Sweden.","DOI":"10.1109\/SAS54819.2022.9881386"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ad\u0131n, V., Zhang, Y., Oelmann, B., and Bader, S. (2023, January 22\u201325). Tiny Machine Learning for Damage Classification in Concrete Using Acoustic Emission Signals. Proceedings of the 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Kuala Lumpur, Malaysia.","DOI":"10.1109\/I2MTC53148.2023.10175972"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1111\/mice.12411","article-title":"Damage classification for masonry historic structures using convolutional neural networks based on still images","volume":"33","author":"Wang","year":"2018","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1111\/mice.12387","article-title":"Road damage detection and classification using deep neural networks with smartphone images","volume":"33","author":"Maeda","year":"2018","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1111\/mice.12263","article-title":"Deep learning-based crack damage detection using convolutional neural networks","volume":"32","author":"Cha","year":"2017","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ercan, E., Avc\u0131, M.S., Pekedis, M., and H\u0131zal, \u00c7. (2024). Damage Classification of a Three-Story Aluminum Building Model by Convolutional Neural Networks and the Effect of Scarce Accelerometers. Appl. Sci., 14.","DOI":"10.3390\/app14062628"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zoubir, H., Rguig, M., El Aroussi, M., Chehri, A., Saadane, R., and Jeon, G. (2022). Concrete bridge defects identification and localization based on classification deep convolutional neural networks and transfer learning. Remote Sens., 14.","DOI":"10.3390\/rs14194882"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1007\/s10586-016-0667-5","article-title":"A load balancing scheme based on deep-learning in IoT","volume":"20","author":"Kim","year":"2017","journal-title":"Clust. Comput."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"103954","DOI":"10.1016\/j.jobe.2021.103954","article-title":"Structural health monitoring of civil engineering structures by using the internet of things: A review","volume":"48","author":"Mishra","year":"2022","journal-title":"J. Build. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1145\/2831347.2831354","article-title":"Edge-centric computing: Vision and challenges","volume":"45","author":"Montresor","year":"2015","journal-title":"Comput. Commun. Rev."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"100461","DOI":"10.1016\/j.iot.2021.100461","article-title":"Tinyml meets iot: A comprehensive survey","volume":"16","author":"Dutta","year":"2021","journal-title":"Internet Things"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ad\u0131n, V., Zhang, Y., And\u00f2, B., Oelmann, B., and Bader, S. (2023, January 18\u201320). Tiny Machine Learning for Real-Time Postural Stability Analysis. Proceedings of the 2023 IEEE Sensors Applications Symposium (SAS), Ottawa, ON, Canada.","DOI":"10.1109\/SAS58821.2023.10254126"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1109\/MIM.2023.10238387","article-title":"Instrumentation and Measurement Systems: Methods, Applications and Opportunities for Instrumentation and Measurement","volume":"26","author":"Bader","year":"2023","journal-title":"IEEE Instrum. Meas. Mag."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Martinez-Rau, L.S., Ad\u0131n, V., Giovanini, L.L., Oelmann, B., and Bader, S. (2023, January 18\u201320). Real-Time Acoustic Monitoring of Foraging Behavior of Grazing Cattle Using Low-Power Embedded Devices. Proceedings of the 2023 IEEE Sensors Applications Symposium (SAS), Ottawa, ON, Canada.","DOI":"10.1109\/SAS58821.2023.10254175"},{"key":"ref_29","first-page":"1","article-title":"On-Device Feeding Behavior Analysis of Grazing Cattle","volume":"73","author":"Chelotti","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e2420","DOI":"10.1002\/stc.2420","article-title":"Novel moir\u00e9-based crack monitoring system with smartphone interface and cloud processing","volume":"26","author":"Ratnam","year":"2019","journal-title":"Struct. Control Health Monit."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Atanane, O., Mourhir, A., Benamar, N., and Zennaro, M. (2023). Smart Buildings: Water Leakage Detection Using TinyML. Sensors, 23.","DOI":"10.3390\/s23229210"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"James, G.L., Ansaf, R.B., Al Samahi, S.S., Parker, R.D., Cutler, J.M., Gachette, R.V., and Ansaf, B.I. (2023). An Efficient Wildfire Detection System for AI-Embedded Applications Using Satellite Imagery. Fire, 6.","DOI":"10.3390\/fire6040169"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Coffen, B., and Mahmud, M. (2021, January 1\u20132). TinyDL: Edge Computing and Deep Learning Based Real-time Hand Gesture Recognition Using Wearable Sensor. Proceedings of the 2020 IEEE International Conference on E-health Networking, Application and Services (HEALTHCOM), Virtual.","DOI":"10.1109\/HEALTHCOM49281.2021.9399005"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"de Prado, M., Rusci, M., Capotondi, A., Donze, R., Benini, L., and Pazos, N. (2021). Robustifying the deployment of tinyml models for autonomous mini-vehicles. Sensors, 21.","DOI":"10.3390\/s21041339"},{"key":"ref_35","first-page":"4367","article-title":"Calculation method study of settlement process of high filling channel in south-to-north water diversion project","volume":"33","author":"Zhang","year":"2014","journal-title":"Chin. J. Rock Mech. Eng."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"4237","DOI":"10.3233\/JIFS-190767","article-title":"Multi-scale feature extraction and recognition of slope damage in high fill channel based on Gabor-SVM method","volume":"38","author":"Liu","year":"2020","journal-title":"J. Intell. Fuzzy Syst."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Miko\u0142ajczyk, A., and Grochowski, M. (2018, January 9\u201312). Data augmentation for improving deep learning in image classification problem. Proceedings of the 2018 International Interdisciplinary PhD Workshop (IIPhDW), Swinoujscie, Poland.","DOI":"10.1109\/IIPHDW.2018.8388338"},{"key":"ref_39","unstructured":"Jung, A. (2019). Imgaug documentation. Readthedocs. Io Jun, 25."},{"key":"ref_40","unstructured":"Gedraite, E.S., and Hadad, M. (2011, January 14\u201316). Investigation on the effect of a Gaussian Blur in image filtering and segmentation. Proceedings of the Proceedings ELMAR-2011, Zadar, Croatia."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1148","DOI":"10.1109\/TIM.2003.815989","article-title":"A method for estimation and filtering of Gaussian noise in images","volume":"52","author":"Russo","year":"2003","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_42","unstructured":"Targ, S., Almeida, D., and Lyman, K. (2016). Resnet in resnet: Generalizing residual architectures. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Koonce, B., and Koonce, B. (2021). EfficientNet. Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, Apress.","DOI":"10.1007\/978-1-4842-6168-2"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018, January 18\u201322). Shufflenet: An extremely efficient convolutional neural network for mobile devices. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., and Le, Q.V. (2019, January 15\u201320). Mnasnet: Platform-aware neural architecture search for mobile. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18\u201322). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.sysarc.2019.02.008","article-title":"Filter-based deep-compression with global average pooling for convolutional networks","volume":"95","author":"Hsiao","year":"2019","journal-title":"J. Syst. Archit."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Haase, D., and Amthor, M. (2020, January 14\u201319). Rethinking depthwise separable convolutions: How intra-kernel correlations lead to improved mobilenets. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01461"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.neunet.2018.11.005","article-title":"A comparison of deep networks with ReLU activation function and linear spline-type methods","volume":"110","author":"Eckle","year":"2019","journal-title":"Neural Netw."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Lavin, A., and Gray, S. (2016, January 27\u201330). Fast algorithms for convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Abadi, M. (2016, January 18\u201322). TensorFlow: Learning functions at scale. Proceedings of the 21st ACM SIGPLAN International Conference on Functional Programming, Nara, Japan.","DOI":"10.1145\/2951913.2976746"},{"key":"ref_52","unstructured":"Smith, S.L., Kindermans, P.J., Ying, C., and Le, Q.V. (2017). Don\u2019t decay the learning rate, increase the batch size. arXiv."},{"key":"ref_53","first-page":"1","article-title":"Leveraging Acoustic Emission and Machine Learning for Concrete Materials Damage Classification on Embedded Devices","volume":"72","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_54","unstructured":"Zhu, M., and Gupta, S. (2017). To prune, or not to prune: Exploring the efficacy of pruning for model compression. arXiv."},{"key":"ref_55","unstructured":"Chai, S.M. (2020, January 3\u201318). Quantization-guided training for compact TinyML models. Proceedings of the Research Symposium on Tiny Machine Learning, Virtual."},{"key":"ref_56","first-page":"800","article-title":"Tensorflow lite micro: Embedded machine learning for tinyml systems","volume":"3","author":"David","year":"2021","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Preuveneers, D., Verheyen, W., Joos, S., and Joosen, W. (2023, January 11). On the adversarial robustness of full integer quantized TinyML models at the edge. Proceedings of the 2nd International Workshop on Middleware for the Edge, Bologna, Italy.","DOI":"10.1145\/3630180.3631201"},{"key":"ref_58","first-page":"28092","article-title":"Post-training quantization for vision transformer","volume":"34","author":"Liu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_59","unstructured":"(2023, June 09). Machine Learning Toolkit Documentation, 2023. Available online: https:\/\/github.com\/siliconlabs\/mltk."},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Sudharsan, B., Yadav, P., Breslin, J.G., and Ali, M.I. (2021, January 5\u201311). An sram optimized approach for constant memory consumption and ultra-fast execution of ml classifiers on tinyml hardware. Proceedings of the 2021 IEEE International Conference on Services Computing (SCC), Virtual.","DOI":"10.1109\/SCC53864.2021.00045"},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"Sarvajcz, K., Ari, L., and Menyhart, J. (2024). AI on the Road: NVIDIA Jetson Nano-Powered Computer Vision-Based System for Real-Time Pedestrian and Priority Sign Detection. Appl. Sci., 14.","DOI":"10.3390\/app14041440"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/13\/4124\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:04:00Z","timestamp":1760108640000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/13\/4124"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,25]]},"references-count":61,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["s24134124"],"URL":"https:\/\/doi.org\/10.3390\/s24134124","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,25]]}}}