Series DC Arc Fault Detection Based on Ensemble Machine Learning

DC arc faults are dangerous to photovoltaic (PV) systems and can cause serious electric fire hazards and property damage. Because the PV inverter works in a high−frequency pulse width modulation (PWM) control mode, the arc fault detection is prone to nuisance tripping due to PV inverter noises. An arc fault detection method based on the autoregressive (AR) model is proposed. A test platform collects the database of this research according to the UL1699B standard, in which three different types of PV inverters are taken into consideration to make it more generalized. The arc current can be considered a nonstationary random signal while the noise of the PV inverter is not. According to the difference in randomness features between an arc and the noise, a detection method based on the AR model is proposed. The Burg algorithm is used to determine model coefficients, while the Akaike Information Criterion (AIC) is applied to explore the best order of the proposed model. The correlation coefficient difference of the model coefficients plays a role as a criterion to identify if there is an arc fault. Moreover, a prototype circuit based on the TMS320F28033 MCU is built for algorithm verification. Test results show that the proposed algorithm can identify an arc fault without a false positive under different PV inverter conditions. The fault clearing time is between 60 ms to 80 ms, which can meet the requirement of 200 ms specified by the standard.

P125. Development of a novel ensemble machine learning algorithm for prediction of complications and readmission after anterior cervical spinal fusion

Arc faults in electric circuits are recognized as an important cause of fire. The first Arc Fault Circuit Interrupter (AFCI) has been patented in 1980 in the United States. AFCI is a device designed to detect electric arc faults which was prescribed for use by the National Electric Code (NEC, US Wiring Regulation) in January 2008. The NEC describes it as ‘A device intended to provide protection from the effects of arc faults by recognizing characteristics unique to arcing and by functioning to de-energize the circuit when an arc fault is detected’. At the beginning of 2012 the Arc Fault Detection Device (AFDD) began to be introduced into the IEC world, culminating in the publication of Technical Product Standards IEC 62606 ' in August 2013, which sets out the requirements for arc fault protection devices. This paper underlines the importance of preventing electrical fires by using the new technology of AFDDs, which largely extend the protection offered by traditional circuit breakers like MCBs and RCDs. Product standard IEC 62606 and functional tests are reviewed, the functioning of AFDDs is explained and a method to design robust algorithms for arc fault detection is proposed.

Since cyberbullying impacts both individual victims and entire society, research on abusive language and its detection has attracted attention in recent years. Because social media sites like Facebook, Instagram, Twitter, and others are so widely accessible, hate speech, bullying, sexism, racism, aggressive material, harassment, poisonous comments, and other types of abuse have all substantially increased. Due to the critical requirement to detect, regulate, and limit the spread of harmful content on social networking sites, we conducted this study to automate the detection of offensive language or cyberbullying. We created a new Arabic balanced data set to be used in the offensive detection process because having a balanced data set for a model would result in improved accuracy models. Recently, the performance of single classifiers has been improved using ensemble machine learning. The purpose of this study is to examine the effectiveness of several single and ensemble machine learning algorithms in identifying Arabic text that contains foul language and cyberbullying. Applying them to three Arabic datasets, we have selected three machine learning classifiers and three ensemble models for this aim. Two of them are offensive datasets that are readily accessible in the public, while the third one was created. The results showed that the single learner machine learning strategy is inferior to the ensemble machine learning methodology. Voting performs is the best performing trained ensemble machine learning classifier, outperforming the best single learner classifier (65.1%, 76.2%, and 98%) for the same datasets with accuracy scores of (71.1%, 76.7%, and 98.5%) for each of the three datasets used. Finally, we improve the voting technique’s performance through hyperparameter tuning on the Arabic cyberbullying data set.

Although photovoltaic (PV) systems play an essential role in distributed generation systems, they also suffer from serious safety concerns due to DC series arc faults. This paper proposes a lightweight convolutional neural network-based method for detecting DC series arc fault in PV systems to solve this issue. An experimental platform according to UL1699B is built, and current data ranging from 3 A to 25 A is collected. Moreover, test conditions, including PV inverter startup and irradiance mutation, are also considered to evaluate the robustness of the proposed method. Before fault detection, the current data is preprocessed with power spectrum estimation. The lightweight convolutional neural network has a lower computational burden for its fewer parameters, which can be ready for embedded microprocessor-based edge applications. Compared to similar lightweight convolutional network models such as Efficientnet-B0, B2, and B3, the Efficientnet-B1 model shows the highest accuracy of 96.16% for arc fault detection. Furthermore, an attention mechanism is combined with the Efficientnet-B1 to make the algorithm more focused on arc features, which can help the algorithm reduce unnecessary computation. The test results show that the detection accuracy of the proposed method can be up to 98.81% under all test conditions, which is higher than that of general networks.

Fault identification and detection are important to the safety, reliability, and efficiency of photovoltaic (PV) systems. Although PV systems do not have any moving parts, they are highly susceptible to harsh environmental factors and undergo degradation that increase the risk for faults. PV systems are difficult to shut down because they are always energized when exposed to any level of solar irradiation. Therefore, in the event of a fault, PV systems are dangerous to handle and have an increased risk for injury.This dissertation reviews the challenges, limitations, and improved solutions specifically for arc faults on the DC-side of the PV system. Arc faults are a subset of PV faults which occur between an air gap that may have formed from the loose connectors, junction box terminals, compromised wires, faulty soldering, and other PV degradation factors and have a large risk of causing fires in PV systems. Traditional detection methods require a priori knowledge of the PV system, utilize only a narrowband of the arcing frequencies for detection, or require large training datasets for machine learning techniques. To increase the robustness of the arc fault detection device and avoid false alarms from unwanted tripping conditions, a detailed DC arc fault model characterizing the different arc fault states as it burns in the air and a modified pink noise model corresponding to the physical arc fault states in the time-domain is proposed for detailed simulations. The unique operating point behavior of arc faults in PV systems is discussed and new current demodulation algorithm is proposed to filter the current waveform of other external noise without a priori knowledge of the PV system. An autocorrelation coefficient analysis technique is proposed which observes the entire arcing frequency band for detection analysis and simple threshold violation criteria are developed for the detection of the arc fault. The dissertation demonstrates the effectiveness of the new arc fault feature extraction methods and detection in both simulation and experimental results.--Author's abstract

Arc fault detection and identification via non-intrusive current disaggregation

Disastrous natural hazards, such as landslides, floods, and forest fires cause a serious threat to natural resources, assets and human lives. Consequently, landslide risk assessment has become requisite for managing the resources in future. This study was designed to develop four ensemble metaheuristic machine learning algorithms, such as grey wolf optimized based artificial neural network (GW-ANN), grey wolf optimized based random forest (GW-RF), particle swarm optimization optimized based ANN (PSO-ANN), and PSO optimized based RF for modeling rainfall-induced landslide susceptibility (LS) in Aqabat Al-Sulbat, Asir region, Saudi Arabia, which observes landslide frequently. To obtain very high precision and robust prediction from machine learning algorithms, the grey wolf and PSO optimization algorithms were integrated to develop new ensemble machine learning techniques. Subsequently, LS maps produced by training dataset were validated using the receiver operating characteristics (ROC) curve based on the testing dataset. Based on the area under curve (AUC) value of ROC curve, the best method for LS modeling was selected. We developed ROC curve-based sensitivity analysis to investigate the influence of the parameters for LS modeling. The Gumble extreme value distribution was employed to estimate the rainfall at 2, 5, 10, 20, 50, and 100 year return periods. Then, the landslide hazard maps were prepared at different return periods by integrating the best LS model and estimated rainfall at different return periods. The theory of danger pixels was employed to prepare a final risk assessment of the resources, which have been exposed to the landslide. The results showed that 27–42 and 6–15 km2 were predicted as the very high and high LS zones using four ensemble metaheuristic machine learning algorithms. Based on the area under curve (AUC) of ROC, GR-ANN (AUC-0.905) appeared as the best model for LS modeling. The areas under high and very high landslide hazard were gradually increased over the progression of time (26 km2 at the 2 year return period and 40 km2 at the 100 year return period for the high landslide hazard zone, and 6 km2 at the 2 year return period and 20 km2 at the 100 year return period for the very high landslide hazard zone). Similarly, the areas of danger pixel also increased gradually from the 2 to 100 year return periods (37 km2 to 62 km2). Various natural resources, such as scrubland, built up, and sparse vegetation, were identified under risk zone due to landslide hazards. In addition, these resources would be exposed extensively to landslides over the advancement of return periods. Therefore, the outcome of the present study will help planners and scientists to propose high precision management plans for protecting natural resources, which have been exposed to landslides.

Accurate oil palm yield prediction is necessary to sustain oil palm production for food security and economic return. However, there are limited studies on comprehensive mapping and accurate oil palm yield prediction using advanced machine learning algorithms. Using multi-temporal remote sensing data, this paper proposed a new approach to predict oil palm yield based on the normalized difference vegetation index (NDVI) and ensemble machine learning algorithm. ReliefF algorithm with linear projection was employed to select the best combination of spectral indices in oil palm discrimination. Oil palm land cover was classified using random forest (RF) and modified AdaBoost algorithms. A time-series approach known as walk-forward validation was firstly introduced to train the model using the 2016-2019 data and the one-step prediction was performed for 2020 using RF and AdaBoost. Result of the study revealed that the RF model (RMSE = 0.384; MSE = 0.148; MAE = 0.147) outperformed the AdaBoost model (RMSE = 0.410; MSE = 0.168; MAE = 0.176). Our research has demonstrated the value of detailed mapping and subsequent yield prediction by developing a novel approach utilising time-series satellite imagery, ensemble machine learning, and NDVI, which will assist decision-makers in managing their practices related to oil palm.

The DC series arc fault has been a potential fire hazard at the photovoltaic system. The sustained DC series arc can support the enough energy to outbreak of fire so that the proper method to detect the arc fault is needed before the fire ignites. On the contrary of the AC system, the DC series arc don’t have a zero crossing point of the voltage and current. It means that the DC series arc detection is proper to do the detection algorithm based on using the not time domain but frequency domain. The frequency characteristic of the DC series arc fault shows that the certain frequency range helping to classify the arc fault condition or normal condition. The Fast Fourier Transform (FFT) is conducted to make the frequency-based data of the DC series arc fault. To draw a clear frequency feature of the arc, in this paper, the several sampling frequency and sampling numbers are implemented as an analog to digital conversion using TMS320F28033 digital signal processor. The circuit simulating a small photovoltaic system of 300 V 3 A is used to make the actual DC series arc fault and the FFT results of the actual DC series arc are compared and analyzed.

Arc faults can cause a severe electric fire, especially series arc faults. Artificial intelligence (AI)-based arc fault detection methods can have a boasted detection accuracy. However, the complexity and large parameter quantity of the AI-based algorithm will hinder its real-time performance for detecting series arc faults. This paper proposes a lightweight arc fault detection method based on the EffNet module, which can make the algorithm less complex with the same detection accuracy level. An arc fault test platform was constructed to collect arc current data, covering eight types of loads required by the IEC 62606 standard. The raw arc current data are used directly as an input for the proposed algorithm, reducing the module’s complexity. According to features of arc current mainly represented in the time domain, the first and last convolution layers of the EffNet module can be improved. Additionally, the spatially separable convolution is well-tuned and trimmed to achieve a more lightweight and better-performance architecture for arc fault detection called Arc_EffNet. Remarkably, this model achieves an impressive arc detection accuracy of 99.75%. An arc fault detection prototype was built using the Raspberry Pi 4B to evaluate the real-time detecting performance of the proposed method. The experimental results show that the prototype takes a time of about 72 ms to respond to a series arc fault, which can fulfill the requirement of real-time detection for arc faults.

Student’s academic performance is one of the most important parameters for evaluating the standard of any institute. It has become a paramount importance for any institute to identify the student at risk of underperforming or failing or even drop out from the course. Machine Learning techniques may be used to develop a model for predicting student’s performance as early as at the time of admission. The task however is challenging as the educational data required to explore for modelling are usually imbalanced. We explore ensemble machine learning techniques namely bagging algorithm like random forest (rf) and boosting algorithms like adaptive boosting (adaboost), stochastic gradient boosting (gbm), extreme gradient boosting (xgbTree) in an attempt to develop a model for predicting the student’s performance of a private university at Meghalaya using three categories of data namely demographic, prior academic record, personality. The collected data are found to be highly imbalanced and also consists of missing values. We employ k-nearest neighbor (knn) data imputation technique to tackle the missing values. The models are developed on the imputed data with 10 fold cross validation technique and are evaluated using precision, specificity, recall, kappa metrics. As the data are imbalanced, we avoid using accuracy as the metrics of evaluating the model and instead use balanced accuracy and F-score. We compare the ensemble technique with single classifier C4.5. The best result is provided by random forest and adaboost with F-score of 66.67%, balanced accuracy of 75%, and accuracy of 96.94%.

This study is to establish a new approach to estimate river salinity of semi‐arid agricultural watershed and identify drivers by using hydrologic modeling and machine learning. We augmented the limitations of the Soil and Water Assessment Tool (SWAT) to model salinity by coupling with eXtreme Gradient Boosting (XGBoost), a decision‐tree‐based ensemble machine learning algorithm. Streamflow, precipitation, elevation, main reach length, and dominant soil texture of the top two layers were used along with NO3, NO2, and total phosphorus (TP) output from a calibrated SWAT model are used as predictors to Total Dissolved Solids (TDS) in the XGBoost algorithm. Then, the SWAT model simulations of streamflow, NO3+NO2, and TP from 2000 to 2015 are used as inputs of the XGBoost model to predict monthly water TDS distribution along the river. The predicted river water TDS showed a higher concentration as going downstream from El Paso (inlet) through the Hudspeth canal to Fort Quitman (outlet). Finally, this study carried out cause analysis focusing on soil physical characteristics. The soil salinity level is directly affected by the soil permeability and irrigation water. As a result, the highest TDS is shown in sites with silt loam, whereas the lowest TDS was shown in sites with very cobbly soil. Silt soils can hold more water and are slower to drain than soils of a sand type. These analyses can be used to better understand the mitigation of water salinity.

Failure mode classification and bearing capacity prediction for reinforced concrete columns based on ensemble machine learning algorithm

A fire accident is the most tragic incident in human life. Particularly environmental hazards such as forest fires lead loss of wildlife, economy, wealth, human lives and pollution. our research purpose of predict the occurrence of fire incidents using ensemble machine learning models. The goal is to develop an accurate and reliable model that can forecast the occurrence of forest fires based on various environmental factors. The best performance is obtained by the ensemble machine learning model for this work. Comparative study of individual model and ensemble model. If you check all models Decision tree predicts 75.4%, the Random Forest tree predicts 83.2%, the Support Vector Machine predicts 71.8%, and the K nearest neighbour predicts 82.1%. Ensemble models with two combinations of decision tree and random forest tree predicts accuracy is 80.8%. Support vector machine and KNN predicts the accuracy rate is 73.4%. The individual model predicts more accuracy compared to ensemble learning model.