A hybrid of convolutional neural network and long short-term memory network approach to predictive maintenance

<p>Predictive maintenance (PdM) is a successful strategy used to reduce cost by minimizing the breakdown stoppages and production loss. The massive amount of data that results from the integration between the physical and digital systems of the production process makes it possible for deep learning (DL) algorithms to be applied and utilized for fault prediction and diagnosis. This paper presents a hybrid convolutional neural network based and long short-term memory network (CNN-LSTM) approach to a predictive maintenance problem. The proposed CNN-LSTM approach enhances the predictive accuracy and also reduces the complexity of the model. To evaluate the proposed model, two comparisons with regular LSTM and gradient boosting decision tree (GBDT) methods using a freely available dataset have been made. The PdM model based on CNN-LSTM method demonstrates better prediction accuracy compared to the regular LSTM, where the average F-Score increases form 93.34% in the case of regular LSTM to 97.48% for the proposed CNN-LSTM. Compared to the related works the proposed hybrid CNN-LSTM PdM approach achieved better results in term of accuracy.</p>

Machine Learning for Wind Turbine Fault Prediction through the Combination of Datasets from Same Type Turbines

Early fault detection in wind turbines is key to reduce both costs and uncertainty in the generation of energy and operation of these structures. The isolation of many wind farms, especially those offshore, makes scheduled maintenance very costly and on many occasions inefficient. In addition, the downtime of these structures is typically long and a predictive solution is much needed to 1) help prepare for the maintenance procedure beforehand, for instance to avoid delays when waiting for the required resources and components for maintenance to be available and, 2) avoid the possibility of more destructive system failures. Predicting failures in such complex systems requires modeling of multiple components in isolation and as a whole. Physics-based and data-based models are used for this purpose, which have been proven useful in this regard. Specifically, Machine Learning algorithms are proven to be a valuable resource in a wide range of problems in this industry, however a solution capable of accurately predicting the range of faults of a particular type of wind turbine is still a challenge. In this paper, we will introduce the capabilities of machine learning for wind turbine fault prediction, as well as a technique to predict different types of faults. We will compare the performance of two well established machine learning algorithms (namely K-Nearest Neighbour and Random Forest classifiers) on real wind turbine data which have produced great levels of prediction accuracy. We also propose data augmentation methods to help enhance the training of ML models when wind turbine data is scarce by merging data from turbines of the same type.

Machine Learning Assisted Interpretation: Integrated Fault Prediction Extraction Case Study from the Groningen Gas Field, Netherlands

Seismic fault detection using machine learning techniques, in particular the convolution neural network (CNN), is becoming a widely accepted practice in the field of seismic interpretation. Machine learning algorithms are trained to mimic the capabilities of an experienced interpreter by recognizing patterns within seismic data and classifying them. Regardless of the method of seismic fault detection, interpretation or extraction of 3D fault representations from edge evidence or fault probability volumes is routine. Extracted fault representations are important to the understanding of the subsurface geology and are a critical input to upstream workflows including structural framework definition, static reservoir and petroleum system modeling, and well planning and de-risking activities. Efforts to automate the detection and extraction of geological features from seismic data have evolved in line with advances in computer algorithms, hardware, and machine learning techniques. We have developed an assisted fault interpretation workflow for seismic fault detection and extraction, demonstrated through a case study from the Groningen gas field of the Upper Permian, Dutch Rotliegend; a heavily faulted, subsalt gas field located onshore, NE Netherlands. Supervised using interpreter-led labeling, we apply a 2D multi-CNN to detect faults within a 3D pre-stack depth migrated seismic dataset. After prediction, we apply a geometric evaluation of predicted faults, using a principal component analysis (PCA) to produce geometric attribute representations (strike azimuth and planarity) of the fault prediction. Strike azimuth and planarity attributes are used to validate and automatically extract consistent 3D fault geometries, providing geological context to the interpreter and input to dependent workflows more efficiently.

Submarine Cable Detection Method Based on Multisensor Communication

Submarine cable is widely used in today’s oil industry, and it is a much hidden large-scale industrial facility, which vigorously promotes the development of people’s lives. With the widespread use of submarine cables based on multisensor communication, as far as the current situation is concerned, this paper makes a report and summary on the research of submarine cable detection method in shallow sea area (sea area within 200 m). According to the implementation of the project and the way of controlling variables, the current common detection modes are planned, fault prediction, fault diagnosis, fault analysis and summary, and experimental data comparison, and then, we can use Brillouin radio frequency to prevent the occurrence of submarine cable fault, and when the fault occurs, we can detect the fault at the first time. The feedback value range of TTSL electromagnetic detection is very stable, and the Brillouin scattering frequency is within the normal fluctuation range. In deep-sea exploration, TTSL electromagnetic detection can detect faults for submarine cables and will not affect the fault in all aspects of waveform and wavelength. Finally, the best path and future development trend of submarine cable detection method are obtained by analyzing and summarizing the detection data, and a complete scheme plan such as some preventive measures and repair technology is put forward.

Research on Digital Twin and Collaborative Cloud and Edge Computing Applied in Operations and Maintenance in Wind Turbines of Wind Power Farm

For the increasingly prominent problems of wind turbine maintenance, using edge cloud collaboration technology to construct wind farm equipment operation and maintenance framework is proposed, digital twin is used for fault prediction and diagnosis. Framework consists of data source layer, edge computing node layer, public or private cloud. Data source layer solves acquisition and transmission of wind turbine operation and maintenance data, edge computing node layer is responsible for on-site data cloud computing, storage and data transmission to cloud computing layer, receiving cloud computing results, device driving and control. The cloud computing layer completes the big data calculation and storage from wind farm, except that, based on real-time data records, continuous simulation and optimization, correct failure prediction mode, expert database and its prediction software, and edge node interaction and shared intelligence. The research explains that wind turbine uses digital twin to do fault prediction and diagnosis model, condition assessment, feature analysis and diagnosis, life prediction, combining with the probabilistic digital twin model to make the maintenance plan and decision-making method.