Downhole tools are complex electro-mechanical systems that perform critical functions in drilling operations. The electronics within these systems provide vital support, such as control, navigation and front-end data analysis from sensors. Due to the extremely challenging operating conditions, namely high pressure, temperature and vibrational forces, electronics can be subjected to complex failure modes and incur operational downtime. A novel Artificial Intelligence (AI)-driven Condition Based Maintenance (CBM) support system is presented, combining Bottom Hole Assembly (BHA) data with Big Data Analytics (BDA). The key objective of this system is to reduce maintenance costs along with an overall improvement of fleet reliability. As evidenced within the literature review, the application of AI methods to downhole tool maintenance is underrepresented in terms of oil and gas application. We review the BHA electronics failure modes and propose a methodology for BHA-Printed Component Board Assemblies (PCBA) CBM. We compare the results of a Random Forest Classifier (RFC) and a XGBoost Classifier trained on BHA electronics memory data cumulated during 208 missions over a 6 months period, achieving an accuracy of 90 % for predicting PCBA failure. These results are extended into a commercial analysis examining various scenarios of infield failure costs and fleet reliability levels. The findings of this paper demonstrate the value of the BHA-PCBA CBM framework by providing accurate prognosis of operational equipment health leading to reduced costs, minimised Non-Productive Time (NPT) and increased operational reliability. INDEX TERMS Bottom hole assembly, oil drilling, printed component board assembly, dynamic environments, failure modes, condition based maintenance, diagnostics, prognostics, machine learning, artificial intelligence.
Industrial-scale component maintenance is shifting towards novel Predictive Maintenance (PdM) strategies supported by Big Data Analytics (BDA). This has resulted in an increased effort to implement Artificial Intelligence (AI) decision making into new maintenance paradigms. The transition of AI into industry faces significant challenges due to the inherent complexities of industrial operations, such as variability in components due to manufacturing, integration, dynamic operating environments and variable loading conditions. Therefore, AI in critical industrial systems requires more advanced capabilities such as robustness, scalability and verifiability. This paper presents the first Deep Learning (DL) based strategy for the classification of the State-Of-Health (SOH) of Electromagnetic Relays (EMR). The DL strategy scales with high-volumes of multivariate time-series data whilst automating labour intensive feature extraction requirements. The method proposed in our paper, combines a Convolutional-Auto-Encoder (CAE) with a Temporal Convolutional Neural Network (TCN), referred to as EMR-SOH CAE-TCN pipeline. Model uncertainty and SOH confidence bounds are approximated by Monte-Carlo dropout. Our pipeline is trained and evaluated on data generated from EMR life-cycle tests. We report a high classification accuracy and discriminatory power of the EMR-SOH classifier. The findings from our paper demonstrate the potential of AI pipelines for maintenance decision making of components in critical applications, providing a transferable AI based PdM solution that scales with large data quantities.
Electromagnetic Relays (Electromagnetic Relay (EMR)s) are omnipresent in electrical systems, ranging from mass-produced consumer products to highly specialised, safety-critical industrial systems. Our detailed literature review focused on EMR reliability highlighting the methods used to estimate the State of Health or the Remaining Useful Life emphasises the limited analysis and understanding of expressive EMR degradation indicators, as well as accessibility and use of EMR life cycle data sets. Prioritising these open challenges, a deep learning pipeline is presented in a prognostic context termed Electromagnetic Relay Useful Actuation Pipeline (EMRUA). Leveraging the attributes of causal convolution, a Temporal Convolutional Network (TCN) based architecture integrates an arbitrary long sequence of multiple features to produce a remaining useful switching actuations forecast. These features are extracted from raw, high volume life cycle data sets, namely EMR switching data (Contact-Voltage, Contact-Current). Monte-Carlo Dropout is utilised to estimate uncertainty during inference. The TCN hyperparameter space, as well as various methods to select and analyse long sequences of multivariate time series data are investigated. Subsequently, our results demonstrate improvements using the developed statistical feature-set over traditional, time-based features, commonly found in literature. EMRUA achieves an average forecasting mean absolute percentage error of ±12 % over the course of the entire EMR life. INDEX TERMSElectromagnetic relay, prognostics, prognostics and health management, predictive maintenance, remaining useful life, artificial intelligence, deep learning, temporal convolutional networks, Monte-Carlo dropout. ABBREVIATIONS AT Arcing time. BT Bounce time. CAE Convolutional auto encoder. CC Coil current. CI Contact current. CNN Convolutional neural network. CR Contact resistance. CT Closing time. CV Contact voltage. DCR Dynamic contact resistance. DI Degradation indicator. EI Exponential indexing. The associate editor coordinating the review of this manuscript and approving it for publication was Sajid Ali . EMR Electromagnetic relay. EMRUA Electromagnetic relay useful actuation pipeline. EOL End of life. FC Fully connected layer. GI Growing-sequence indexing. LI Linear indexing. LSTM Long-short-term-memory network. MAE Mean absolute error. MAPE Mean absolute percentage error. MCD Monte-carlo dropout. MVTD Multivariate time series data. NN Neural network. OT Over-travel time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.