关键词： Rate of penetration (ROP)   Machine learning   Artificial neural networks (ANNs)   Support vector machine (SVM)   Meta-heuristic algorithms   Fuzzy logic (FL)  

摘要： Rate of penetration (ROP) management is a matter of importance in drilling operations and it has been considered in different studies. Different machine learning methods such as simple and optimized artificial neural networks (ANNs), support vector machines (SVMs), fuzzy logic (FL) or adaptive neuro-fuzzy inference system (ANFIS), ensemble methods of machine learning and meta-heuristic algorithms have been used for this purpose so far. In this article, some of the studies by using these methods as the main approach for ROP management are reviewed to achieve a better understanding of this concept, its economic benefits and also its research capacities. Results indicate that ANNs are the most popular machine learning method in ROP management, while simple ANNs excel the modified types in this regard. Still, modified ANNs outperform simple ones in terms of prediction accuracy, but as ANNs fall short in superior prediction performance, other machine learning approaches of ROP management such as linear regression (LR), random forest (RF) and gradient boosting method (GBM) have compensated this shortcoming and proved their efficiency and applicability.

关键词： guyed tower   finite element   wind loading   machine learning   autoencoder  

摘要： This paper presents the development of a methodology to detect and evaluate faults in cable-stayed towers, which are part of the infrastructure of Brazil's interconnected electrical system. The proposed method increases system reliability and minimizes the risk of service failure and tower collapse through the introduction of predictive maintenance methods based on artificial intelligence, which will ultimately benefit the end consumer. The proposed signal processing and interpretation methods are based on a machine learning approach, where the tower vibration is acquired from accelerometers that measure the dynamic response caused by the effects of the environment on the towers through wind and weather conditions. Data-based models were developed to obtain a representation of health degradation, which is primarily based on the finite element model of the tower, subjected to wind excitation. This representation is also based on measurements using a mockup tower with different types of provoked degradation that was subjected to ambient changes in the laboratory. The sensor signals are preprocessed and submitted to an autoencoder neural network to minimize the dimensionality of the resources involved, being analyzed by a classifier, based on a Softmax configuration. The results of the proposed configuration indicate the possibility of early failure detection and evolution evaluation, providing an effective failure detection and monitoring system.

关键词： artificial neural networks   graphene   machine learning   silent speech recognition   strain gauge  

摘要： Silent speech recognition is the ability to recognise intended speech without audio information. Useful applications can be found in situations where sound waves are not produced or cannot be heard. Examples include speakers with physical voice impairments or environments in which audio transference is not reliable or secure. Developing a device which can detect non-auditory signals and map them to intended phonation could be used to develop a device to assist in such situations. In this work, we propose a graphene-based strain gauge sensor which can be worn on the throat and detect small muscle movements and vibrations. Machine learning algorithms then decode the non-audio signals and create a prediction on intended speech. The proposed strain gauge sensor is highly wearable, utilising graphene's unique and beneficial properties including strength, flexibility and high conductivity. A highly flexible and wearable sensor able to pick up small throat movements is fabricated by screen printing graphene onto lycra fabric. A framework for interpreting this information is proposed which explores the use of several machine learning techniques to predict intended words from the signals. A dataset of 15 unique words and four movements, each with 20 repetitions, was developed and used for the training of the machine learning algorithms. The results demonstrate the ability for such sensors to be able to predict spoken words. We produced a word accuracy rate of 55% on the word dataset and 85% on the movements dataset. This work demonstrates a proof-of-concept for the viability of combining a highly wearable graphene strain gauge and machine leaning methods to automate silent speech recognition.

关键词： ICESat-2   Sentinel-1   Sentinel-2   topographic information   forest canopy height   machine learning   forest type  

摘要： Spaceborne LiDAR has been widely used to obtain forest canopy heights over large areas, but it is still a challenge to obtain spatio-continuous forest canopy heights with this technology. In order to make up for this deficiency and take advantage of the complementary for multi-source remote sensing data in forest canopy height mapping, a new method to estimate forest canopy height was proposed by synergizing the spaceborne LiDAR (ICESat-2) data, Synthetic Aperture Radar (SAR) data, multi-spectral images, and topographic data considering forest types. In this study, National Geographical Condition Monitoring (NGCM) data was used to extract the distributions of coniferous forest (CF), broadleaf forest (BF), and mixed forest (MF) in Hua' nan forest area in Heilongjiang Province, China. Accordingly, the forest canopy height estimation models for whole forest (all forests together without distinguishing types, WF), CF, BF, and MF were established, respectively, by Radom Forest (RF) and Gradient Boosting Decision Tree (GBDT). The accuracy for established models and the forest canopy height obtained based on estimation models were validated consequently. The results showed that the forest canopy height estimation models considering forest types had better performance than the model grouping all types of forest together. Compared with GBDT, RF with optimal variables had better performance in forest canopy height estimation with Pearson's correlation coefficient (R) and the root-mean-squared error (RMSE) values for CF, BF, and MF of 0.72, 0.59, 0.62, and 3.15, 3.37, 3.26 m, respectively. It has been validated that a synergy of ICESat-2 with other remote sensing data can make a crucial contribution to spatio-continuous forest canopy height mapping, especially for areas covered by different types of forest.

关键词： Power system operation   Transformer fault diagnosis   Explainable machine learning   Extreme gradient boosted trees   Feature selection   Dissolved gas analysis  

摘要： Power transformer faults are considered rare events, so data samples in normal operations are much more readily available than in faulty conditions. Traditionally, power transformer fault diagnoses were enabled through gasin-oil data, where erroneous diagnoses of faulty conditions as normal could have a more significant effect on power system operations than wrong diagnoses of normal operations as a faulty condition. Therefore, it is imperative to analyze gas-in-oil data characteristics more effectively to improve the performance of diagnostic methods. In this paper, an explainable bi-level machine learning method is proposed for oil-immersed power transformer fault diagnoses, consisting of a binary imbalanced classification model and a multi-classification model. The proposed Extreme Gradient Boosting models are designed with custom functions at each level, and automatic hyperparameters tuning is conducted based on Bayesian optimization. A fault feature selection is developed using the SHapley Additive exPlanations method to explain the diagnosis results, which could mine the impacts of fault features on diagnosis results and find the approach to improve the model performance. The fault diagnosis results are presented with performance analysis and comparative studies, and the feature selection results with importance analysis for each fault type based on SHAP value is provided, which demonstrates the feasibility and effectiveness of the proposed method.

关键词： landslide susceptibility mapping   convolutional neural network   machine learning   GIS   Jiuzhaigou region   Lantau Island  

摘要： Landslide susceptibility mapping (LSM) is a useful tool to estimate the probability of landslide occurrence, providing a scientific basis for natural hazards prevention, land use planning, and economic development in landslide-prone areas. To date, a large number of machine learning methods have been applied to LSM, and recently the advanced convolutional neural network (CNN) has been gradually adopted to enhance the prediction accuracy of LSM. The objective of this study is to introduce a CNN-based model in LSM and systematically compare its overall performance with the conventional machine learning models of random forest, logistic regression, and support vector machine. Herein, we selected Zhangzha Town in Sichuan Province, China, and Lantau Island in Hong Kong, China, as the study areas. Each landslide inventory and corresponding predisposing factors were stacked to form spatial datasets for LSM. The receiver operating characteristic analysis, area under the curve (AUC), and several statistical metrics, such as accuracy, root mean square error, Kappa coefficient, sensitivity, and specificity, were used to evaluate the performance of the models. Finally, the trained models were calculated, and the landslide susceptibility zones were mapped. Results suggest that both CNN and conventional machine learning-based models have a satisfactory performance. The CNN-based model exhibits an excellent prediction capability and achieves the highest performance but also significantly reduces the salt-of-pepper effect, which indicates its great potential for application to LSM.

关键词： hail size   FY-4A   machine learning   principal component analysis   neural network  

摘要： The magnitude of damage caused by hail depends on its size;however, direct observation or indirect estimation of hail size remains a significant challenge. One primary reason for estimations by proxy, such as through remote sensing methods, is that empirical relationships or statistical models established in one region may not apply to other areas. This study employs a machine learning method to build a hail size estimation model without assuming relations in advance. It uses FY-4A AGRI data to provide cloud-top information and ERA5 data to add vertical environment information. Before training the model, we conducted a principal component analysis (PCA) to analyze the highly influential factors on hail sizes. A total of 18 features, composed of four groups, namely brightness temperature (BT), the difference in BT (BTD), thermodynamics, and dynamics groups, were chosen from 29 original features. Dynamic and BTD features show superior performance in identifying large hail. Although the selected features are more closely correlated to hail sizes than unselected ones, the relationships are complicated and nonlinear. As a result, a two-layer regression back propagation neural network (BPNN) model with powerful fitting ability is trained with selected features to predict maximum hail diameter (MHD). The linear fitting R-2 between predicted and observed MHDs is 0.52 on the test set, which signifies that our model performs well compared with other hail size estimation models. We also examine the model concerning all three hail cases in Shanghai, China, between 2019 and 2021. The model attained more satisfactory results than the radar-based maximum estimated hail size (MEHS) method, which overestimates the MHDs, thus further supporting the operational applications of our model.

关键词： incremental sheet forming   failure prevention   friction force   robotized manufacturing   prediction model  

摘要： This paper proposes a method for extracting information from the parameters of a single point incremental forming (SPIF) process. The measurement of the forming force using this technology helps to avoid failures, identify optimal processes, and to implement routine control. Since forming forces are also dependent on the friction between the tool and the sheet metal, an innovative solution has been proposed to actively control the friction forces by modulating the vibrations that replace the environmentally unfriendly lubrication of contact surfaces. This study focuses on the influence of mechanical properties, process parameters and sheet thickness on the maximum forming force. Artificial Neural Network (ANN) and different machine learning (ML) algorithms have been applied to develop an efficient force prediction model. The predicted forces agreed reasonably well with the experimental results. Assuming that the variability of each input function is characterized by a normal distribution, sampling data were generated. The applicability of the models in an industrial environment is due to their relatively high performance and the ability to balance model bias and variance. The results indicate that ANN and Gaussian process regression (GPR) have been identified as the most efficient methods for developing forming force prediction models.

关键词： leaf area index (LAI)   light extinction coefficient   unmanned aerial vehicles (UAV)   multispectral data   RGB data   machine learning   pergola-trained vineyards  

摘要： The leaf area index (LAI), a valuable variable for assessing vine vigor, reflects nutrient concentrations in vineyards and assists in precise management, including fertilization, improving yield, quality, and vineyard uniformity. Although some vegetation indices (VIs) have been successfully used to assess LAI variations, they are unsuitable for vineyards of different types and structures. By calibrating the light extinction coefficient of a digital photography algorithm for proximal LAI measurements, this study aimed to develop VI-LAI models for pergola-trained vineyards based on high-resolution RGB and multispectral images captured by an unmanned aerial vehicle (UAV). The models were developed by comparing five machine learning (ML) methods, and a robust ensemble model was proposed using the five models as base learners. The results showed that the ensemble model outperformed the base models. The highest R-2 and lowest RMSE values that were obtained using the best combination of VIs with multispectral data were 0.899 and 0.434, respectively;those obtained using the RGB data were 0.825 and 0.547, respectively. By improving the results by feature selection, ML methods performed better with multispectral data than with RGB images, and better with higher spatial resolution data than with lower resolution data. LAI variations can be monitored efficiently and accurately for large areas of pergola-trained vineyards using this framework.

关键词： Linac   Electron beam parameters   Monte Carlo simulation   Statistical method   Multivariate analysis   Machine learning  

摘要： Purpose: This study aimed to determine the optimal initial electron beam parameters of a Linac for radiotherapy with a multivariate approach using statistical and machine-learning tools. Methods: For MC beam commissioning, a 6 MV Varian Clinac was simulated using the Geant4 toolkit. The authors investigated the relations between simulated dose distribution and initial electron beam parameters, namely, mean energy (E), energy spread (ES), and radial beam size (RS). The goodness of simulation was evaluated by the slope of differences between the simulated and the golden beam data. The best-fit combination of the electron beam parameters that minimized the slope of dose difference was searched through multivariate methods using conventional statistical methods and machine-learning tools of the scikit-learn library. Results: Simulation results with 87 combinations of the electron beam parameters were analyzed. Regardless of being univariate or multivariate, traditional statistical models did not recommend a single parameter set simultaneously minimizing slope of dose differences for percent depth dose (PDD) and lateral dose profile (LDP). Two machine learning classification modules, RandomForestClassifier and BaggingClassifier, agreed in recommending (E = 6.3 MeV, ES = +/- 5.0%, RS = 1.0 mm) for predicting simultaneous acceptance of PDD and LDP. Conclusions: The machine learning with random-forest and bagging classifier modules recommended a consistent result. It was possible to draw an optimal electron beam parameter set using multivariate methods for MC simulation of a radiotherapy 6 MV Linac.