In order to improve the rolling bearing fault diagnosis accuracy, a rolling bearing fault diagnosis method with Variational Modal Decomposition (VMD), t-distributed domain embedding (t-SNE) and genetic algorithm optimized least squares support vector machine (GA-LSSVM) is proposed. Firstly, the bearing signal is decomposed into several intrinsic modal components (IMFs) by applying VMD; secondly, the time-frequency eigen indices of each IMF are calculated to compose the high-dimensional fault features, and the t-SNE algorithm is utilized for the secondary feature extraction, which reduces the influence of redundant features on fault diagnosis. Finally, the low-dimensional sensitive features are used as inputs to the GA-LSSVM model. Experimental analysis shows that the model based on t-SNE-GA-LSSVM has high fault diagnosis accuracy, good stability
In order to improve the accuracy of diagnosis, a fault diagnosis and research method of gearbox bearing of wind turbine based on ICEEMDAN-PE and GWO-LSSVM is proposed. The method firstly uses ICEEMDAN to decompose the sampled data signals, then uses PE to extract the features, and finally inputs the features into Grey Wolf algorithm (GWO) to optimize the Least Squares Support Vector Machine (LSSVM) diagnostic model to train the optimal parameters. A fault diagnosis model is built to identify common faults in gearbox bearings accurately. Combined with the simulation experimental data, the diagnosis accuracy is 97.67%, which proves the feasibility of the scheme, and provides an effective method for improving the accuracy of the gearbox bearing fault diagnosis
KEYWORDS: Decision making, Mathematical optimization, Photovoltaics, Solar cells, Power supplies, Pollution, Fuzzy logic, Wind turbine technology, Systems modeling, Solar energy
To solve the multi-objective problem of microgrid scheduling, it can be comprehensively considered from three aspects: economy, technology and environment. In terms of evaluation, an economic index model is established to minimize power generation and transaction costs, and a technical index model with minimum network loss and an environmental index model with the lowest pollution gas treatment costs is adopted. In order to select an optimal combination strategy, Pareto optimal solution method is used to solve the multi-objective optimization problem of microgrid, and a double positive distance decision method (ECDPD-MCDM) considering equivalence is proposed to select a reasonable compromise optimal solution for decision makers. The experimental results show that the proposed selection strategy can select a reasonable compromise optimal solution from the optimal solution set, and embodies certain preference.
In order to solve the problem of low transformer fault recognition rate, this paper proposes a fault diagnosis method based on feature selection and improved bald eagle search algorithm (IBES) to optimize random forest (RF). Firstly, to solve the problem that the specific gravity of dissolved gas in transformer oil is difficult to diagnose efficiently, this paper proposes to use 7 ratio relations between five gases and the specific gravity of the original five gases as fault characteristics, and use RF for feature selection. Secondly, to solve the problem of low convergence accuracy of the Bald eagle search algorithm (BES), this paper uses Sine chaotic mapping, Levy flight and Cauchy Gaussian variation perturbation strategy to improve BES. Finally, in order to improve the diagnostic accuracy of RF model, IBES is used to optimize RF parameters and build IBES-RF model. The simulation results show that compared with BES-RF and PSO-RF models, IBES-RF has the best fault diagnosis effect, and the accuracy rate is 90.51%.
In order to address the low accuracy of existing transformer fault diagnosis techniques, this research suggests an unique transformer fault diagnostic model based on an improved whale algorithm optimized extreme gradient boosting (IWOA-XGBoost). First, based on Dissolved Gas Analysis (DGA) of oil, nine gas ratios were created utilizing the no coding ratio approach; Then use the hybrid strategy to improve the traditional WOA; Finally, IWOA is constructed to optimize XGBoost for transformer fault diagnosis. As compared to other algorithms, the accuracy rates of the experimental findings show that the model put forward in this study is superior, increasing by 16.89%, 11.69%, 6.5%, 3.9%, and 1.3%, respectively.
For the detect recognition of transmission line insulators, there are some problems for the traditional fault recognition algorithms, such as false detection, omission of detection, low and slow recognition rate. Compared with the traditional convolutional neural networks, vector is used by the capsule network as the input. Each sub-structure of the capsule makes the details highly fidelity in the original graph, which can effectively identify the defective insulator image. Therefore, a detect recognition method based on improved capsule network and YOLO-V5 is proposed in this paper. Experimental results demonstrate that the algorithm performs well and meets the requirements for inspecting insulators.
In response to the problem of drone avoidance problems under low energy visibility, a laser point cloud power line positioning method was proposed. This method solves ground equations by POS data instead of traditional iterative methods to improve system real time performance. Then reduce the number of clouds through sub-sampling. Then use Euclidean clustering to separate target point clouds. Because the power line point cloud is different from the targets such as common vehicles, architecture and other goals, has low density and non-rigidity characteristics, we use the point cloud registration method to obtain the power line position. For this purpose, this method has built a power line model with a range of ten meters and collects multiple power line cloud data as experimental materials. The results show that the method can obtain the target power line position quickly and accurately in the selected scenes.
Aimed at the difficulties in extracting fault features and low diagnostic accuracy of rolling bearings, an intelligent diagnosis method which combines the Variational Mode Decomposition, Envelope Spectrum Analysis and the Optimized Gradient Boosted Random Forest Model is proposed. Firstly, low-pass filtering is used to denoise the measured vibration signal of rolling bearings, and then VMD is used to decompose the processed vibration signal, and the instantaneous energy matrix of the Intrinsic Mode Functions (IMFs) obtained by VMD is calculated by ESA. Then use Principal Components Analysis (PCA) to perform feature extraction on the obtained instantaneous energy matrixes. Finally, put the extracted feature vectors into the gradient boosted random forest model optimized by sparrow search algorithm for fault diagnosis of rolling bearings and the accuracy of fault diagnosis is calculated by cross-validation. The experimental result shows that this method can accurately extract the features of rolling bearings in different fault states, which has a high accuracy in the fault diagnosis of rolling bearings.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.