Scholarly Work - Electrical & Computer Engineering
Permanent URI for this collectionhttps://scholarworks.montana.edu/handle/1/8814
Browse
6 results
Search Results
Item Comparison of Supervised Learning and Changepoint Detection for Insect Detection in Lidar Data(MDPI AG, 2023-12) Vannoy, Trevor C.; Sweeney, Nathaniel B.; Shaw, Joseph A.; Whitaker, Bradley M.Concerns about decreases in insect population and biodiversity, in addition to the need for monitoring insects in agriculture and disease control, have led to an increased need for automated, non-invasive monitoring techniques. To this end, entomological lidar systems have been developed and successfully used for detecting and classifying insects. However, the data produced by these lidar systems create several problems from a data analysis standpoint: the data can contain millions of observations, very few observations contain insects, and the background environment is non-stationary. This study compares the insect-detection performance of various supervised machine learning and unsupervised changepoint detection algorithms and provides commentary on the relative strengths of each method. We found that the supervised methods generally perform better than the changepoint detection methods, at the cost of needing labeled data. The supervised learning method with the highest Matthew’s Correlation Coefficient score on the testing set correctly identified 99.5% of the insect-containing images and 83.7% of the non-insect images; similarly, the best changepoint detection method correctly identified 83.2% of the insect-containing images and 84.2% of the non-insect images. Our results show that both types of methods can reduce the need for manual data analysis.Item Distribution System State Estimation Using Hybrid Traditional and Advanced Measurements for Grid Modernization(MDPI AG, 2023-06) Radhoush, Sepideh; Vannoy, Trevor; Liyanage, Kaveen; Whitaker, Bradley M.; Nehrir, HashemDistribution System State Estimation (DSSE) techniques have been introduced to monitor and control Active Distribution Networks (ADNs). DSSE calculations are commonly performed using both conventional measurements and pseudo-measurements. Conventional measurements are typically asynchronous and have low update rates, thus leading to inaccurate DSSE results for dynamically changing ADNs. Because of this, smart measurement devices, which are synchronous at high frame rates, have recently been introduced to enhance the monitoring and control of ADNs in modern power networks. However, replacing all traditional measurement devices with smart measurements is not feasible over a short time. Thus, an essential part of the grid modernization process is to use both traditional and advanced measurements to improve DSSE results. In this paper, a new method is proposed to hybridize traditional and advanced measurements using an online machine learning model. In this work, we assume that an ADN has been monitored using traditional measurements and the Weighted Least Square (WLS) method to obtain DSSE results, and the voltage magnitude and phase angle at each bus are considered as state vectors. After a period of time, a network is modified by the installation of advanced measurement devices, such as Phasor Measurement Units (PMUs), to facilitate ADN monitoring and control with a desired performance. Our work proposes a method for taking advantage of all available measurements to improve DSSE results. First, a machine-learning-based regression model was trained from DSSE results obtained using only the traditional measurements available before the installation of smart measurement devices. After smart measurement devices were added to the network, the model predicted traditional measurements when those measurements were not available to enable synchronization between the traditional and smart sensors, despite their different refresh rates. We show that the regression model had improved performance under the condition that it continued to be updated regularly as more data were collected from the measurement devices. In this way, the training model became robust and improved the DSSE performance, even in the presence of more Distributed Generations (DGs). The results of the proposed method were compared to traditional measurements incorporated into the DSSE calculation using a sample-and-hold technique. We present the DSSE results in terms of Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) values for all approaches. The effectiveness of the proposed method was validated using two case studies in the presence of DGs: one using a modified IEEE 33-bus distribution system that considered loads and DGs based on a Monte Carlo simulation and the other using a modified IEEE 69-bus system that considered actual data for loads and DGs. The DSSE results illustrate that the proposed method is better than the sample-and-hold method.Item Distribution System State Estimation and False Data Injection Attack Detection with a Multi-Output Deep Neural Network(MDPI AG, 2023-02) Radhoush, Sepideh; Vannoy, Trevor; Liyanage, Kaveen; Whitaker, Bradley M.; Nehrir, HashemDistribution system state estimation (DSSE) has been introduced to monitor distribution grids; however, due to the incorporation of distributed generations (DGs), traditional DSSE methods are not able to reveal the operational conditions of active distribution networks (ADNs). DSSE calculation depends heavily on real measurements from measurement devices in distribution networks. However, the accuracy of real measurements and DSSE results can be significantly affected by false data injection attacks (FDIAs). Conventional FDIA detection techniques are often unable to identify FDIAs into measurement data. In this study, a novel deep neural network approach is proposed to simultaneously perform DSSE calculation (i.e., regression) and FDIA detection (i.e., binary classification) using real measurements. In the proposed work, the classification nodes in the DNN allow us to identify which measurements on which phasor measurement unit (PMU), if any, were affected. In the proposed approach, we aim to show that the proposed method can perform DSSE calculation and identify FDIAs from the available measurements simultaneously with high accuracy. We compare our proposed method to the traditional approach of detecting FDIAs and performing SE calculations separately; moreover, DSSE results are compared with the weighted least square (WLS) algorithm, which is a common model-based method. The proposed method achieves better DSSE performance than the WLS method and the separate DSSE/FDIA method in presence of erroneous measurements; our method also executes faster than the other methods. The effectiveness of the proposed method is validated using two FDIA schemes in two case studies: one using a modified IEEE 33-bus distribution system without DGs, and the other using a modified IEEE 69-bus system with DGs. The results illustrated that the accuracy and F1-score of the proposed method are better than when performing binary classification only. The proposed method successfully detected the FDIAs on each PMU measurement. Moreover, the results of DSSE calculation from the proposed method has a better performance compared to the regression-only method, and the WLS methods in the presence of bad data.Item Distribution System State Estimation and False Data Injection Attack Detection with a Multi-Output Deep Neural Network(MDPI AG, 2023-02) Radhoush, Sepideh; Vannoy, Trevor; Liyanage, Kaveen; Whitaker, Bradley M.; Nehrir, HashemDistribution system state estimation (DSSE) has been introduced to monitor distribution grids; however, due to the incorporation of distributed generations (DGs), traditional DSSE methods are not able to reveal the operational conditions of active distribution networks (ADNs). DSSE calculation depends heavily on real measurements from measurement devices in distribution networks. However, the accuracy of real measurements and DSSE results can be significantly affected by false data injection attacks (FDIAs). Conventional FDIA detection techniques are often unable to identify FDIAs into measurement data. In this study, a novel deep neural network approach is proposed to simultaneously perform DSSE calculation (i.e., regression) and FDIA detection (i.e., binary classification) using real measurements. In the proposed work, the classification nodes in the DNN allow us to identify which measurements on which phasor measurement unit (PMU), if any, were affected. In the proposed approach, we aim to show that the proposed method can perform DSSE calculation and identify FDIAs from the available measurements simultaneously with high accuracy. We compare our proposed method to the traditional approach of detecting FDIAs and performing SE calculations separately; moreover, DSSE results are compared with the weighted least square (WLS) algorithm, which is a common model-based method. The proposed method achieves better DSSE performance than the WLS method and the separate DSSE/FDIA method in presence of erroneous measurements; our method also executes faster than the other methods. The effectiveness of the proposed method is validated using two FDIA schemes in two case studies: one using a modified IEEE 33-bus distribution system without DGs, and the other using a modified IEEE 69-bus system with DGs. The results illustrated that the accuracy and F1-score of the proposed method are better than when performing binary classification only. The proposed method successfully detected the FDIAs on each PMU measurement. Moreover, the results of DSSE calculation from the proposed method has a better performance compared to the regression-only method, and the WLS methods in the presence of bad data.Item Distribution System State Estimation and False Data Injection Attack Detection with a Multi-Output Deep Neural Network(MDPI AG, 2023-02) Radhoush, Sepideh; Vannoy, Trevor; Liyanage, Kaveen; Whitaker, Bradley M.; Nehrir, HashemDistribution system state estimation (DSSE) has been introduced to monitor distribution grids; however, due to the incorporation of distributed generations (DGs), traditional DSSE methods are not able to reveal the operational conditions of active distribution networks (ADNs). DSSE calculation depends heavily on real measurements from measurement devices in distribution networks. However, the accuracy of real measurements and DSSE results can be significantly affected by false data injection attacks (FDIAs). Conventional FDIA detection techniques are often unable to identify FDIAs into measurement data. In this study, a novel deep neural network approach is proposed to simultaneously perform DSSE calculation (i.e., regression) and FDIA detection (i.e., binary classification) using real measurements. In the proposed work, the classification nodes in the DNN allow us to identify which measurements on which phasor measurement unit (PMU), if any, were affected. In the proposed approach, we aim to show that the proposed method can perform DSSE calculation and identify FDIAs from the available measurements simultaneously with high accuracy. We compare our proposed method to the traditional approach of detecting FDIAs and performing SE calculations separately; moreover, DSSE results are compared with the weighted least square (WLS) algorithm, which is a common model-based method. The proposed method achieves better DSSE performance than the WLS method and the separate DSSE/FDIA method in presence of erroneous measurements; our method also executes faster than the other methods. The effectiveness of the proposed method is validated using two FDIA schemes in two case studies: one using a modified IEEE 33-bus distribution system without DGs, and the other using a modified IEEE 69-bus system with DGs. The results illustrated that the accuracy and F1-score of the proposed method are better than when performing binary classification only. The proposed method successfully detected the FDIAs on each PMU measurement. Moreover, the results of DSSE calculation from the proposed method has a better performance compared to the regression-only method, and the WLS methods in the presence of bad data.Item Automatic detection of multilayer hexagonal boron nitride in optical images using deep learning-based computer vision(Springer Science and Business Media LLC, 2023-01) Ramezani, Fereshteh; Parvez, Sheikh; Fix, J. Pierce; Battaglin, Arthur; Whyte, Seamus; Borys, Nicholas J.; Whitaker, Bradley M.Computer vision algorithms can quickly analyze numerous images and identify useful information with high accuracy. Recently, computer vision has been used to identify 2D materials in microscope images. 2D materials have important fundamental properties allowing for their use in many potential applications, including many in quantum information science and engineering. One such material is hexagonal boron nitride (hBN), an isomorph of graphene with a very indistinguishable layered structure. In order to use these materials for research and product development, the most effective method is mechanical exfoliation where single-layer 2D crystallites must be prepared through an exfoliation procedure and then identified using reflected light optical microscopy. Performing these searches manually is a time-consuming and tedious task. Deploying deep learning-based computer vision algorithms for 2D material search can automate the flake detection task with minimal need for human intervention. In this work, we have implemented a new deep learning pipeline to classify crystallites of hBN based on coarse thickness classifications in reflected-light optical micrographs. We have used DetectoRS as the object detector and trained it on 177 images containing hexagonal boron nitride (hBN) flakes of varying thickness. The trained model achieved a high detection accuracy for the rare category of thin flakes (<50 atomic layers thick). Further analysis shows that our proposed pipeline could be generalized to various microscope settings and is robust against changes in color or substrate background.