Total dissolved solids (TDS) is one of the most significant indicators of regulated wastewater effluents, and it is critical in assessing and improving the performance of any wastewater treatment facility. The literat...
详细信息
ISBN:
(数字)9798331534400
ISBN:
(纸本)9798331534417
Total dissolved solids (TDS) is one of the most significant indicators of regulated wastewater effluents, and it is critical in assessing and improving the performance of any wastewater treatment facility. The literature review reveals that the pattern of TDS and other water quality parameters generally shows noisy and complicated features; hence, capturing their pattern is tough. This paper proposes a new approach to noise reduction by Ensemble Empirical Mode Decomposition (EEMD), incorporating machine learning algorithms like Artificial Neural Network (ANN) and Support Vector Machine (SVM) to improve the accuracy of TDS prediction. The data on temperature, pH, turbidity, and TDS were collected from the Bangabandhu Water Treatment Plant (BWTP) in Khulna, Bangladesh. In the current work, traditional and EEMD-based approaches were developed, and the performances of these were evaluated based on MSE, RMSE, and MAE. It is presented that the EEMD-based approach reduced the error considerably over the traditional models, while a maximum reduction of 89.46% and 91.04% in MSE are achieved in ANN and SVM, respectively. It further suggested that the proposed approaches could be applied to other wastewater treatment plants. Practical deployment of this model will help the operators make real-time decisions in optimized treatment processes.
Several methods have been proposed for detection and classification of power quality (PQ). A novel algorithm to detect and identify faults power swings is proposed based on S-Transform and Approximate Shannon Energy (...
详细信息
ISBN:
(纸本)9781467378956
Several methods have been proposed for detection and classification of power quality (PQ). A novel algorithm to detect and identify faults power swings is proposed based on S-Transform and Approximate Shannon Energy (SSE) for power quality analysis. This paper investigates the use and the performance of (SSE). Using real and simulated data, two methods are applied: wavelet analysis, and our approach has been evaluated according to the accuracy of detection of the beginning and end of the disturbance in question. For application, six types of disturbance including a voltage sag, swell, interruption, with and without harmonics were investigated. The proposed method (SSE) has better performance for detection frequency intervals of the disturbances.
This study presents fault detection of a heavy duty V94.2 gas turbine which has 162.1 MW nominal power and 50 Hz nominal frequency and is located at Pareh Sar power plant, Gilan, Iran. For this purpose stored data inc...
详细信息
ISBN:
(纸本)9781467372350
This study presents fault detection of a heavy duty V94.2 gas turbine which has 162.1 MW nominal power and 50 Hz nominal frequency and is located at Pareh Sar power plant, Gilan, Iran. For this purpose stored data include measurements of relative and absolute vibration of shaft bearings in both turbine and compressor sections. signalprocessing techniques and mathematical transformations are used for feature extraction, as well as supervised and unsupervised methods for dimensionality reduction. Finally neural networks are employed for classification task and fault detection results for different methods are compared and discussed. Proposed techniques show zero FAR and MAR, when PNN is used with PCA or when MLP or RBF is used with LDA for dimensionality reduction.
The 3rdinternationalconference on Electrical, Communication and Computer Engineering (ICECCE 2021) was held on 12-13 June, 2021 as a virtual event due to following important reasons. 1) Right now many countries are ...
The 3rdinternationalconference on Electrical, Communication and Computer Engineering (ICECCE 2021) was held on 12-13 June, 2021 as a virtual event due to following important reasons. 1) Right now many countries are facing severe wave/spread of COVID-19, the organizing committee believes that due to unavoidable restrictions and circumstances because of Covid-19, physical arrangement of the conference would be very difficult. 2) There are certain travelling restrictions across the word, therefore travelling to Kuala Lumpur for committee, authors and keynote speakers is either not easy or not possible. 3) Most of the authors do not want the conference to be postponed, because some of them need publication for graduation/degree from their respective institute as a mandatory requirement, therefore, conference will occur on the current dates. This conference offers the opportunity for engineers, scientists, professionals, policymakers, investors, and other parties to review recent developments in the areas related to Electrical, Electronics and Computer and Communication Engineering and Technologies. The conference covers many topics under different fields such as power and energy, smart grids, industrial process control, intelligent bio-medical diagnostic systems, satellite and wireless communications, signal and image processing, embedded systems, networks & security, internet of things & big data and software engineering & agile development etc. The outcome of the lectures, expert discussions and presentations will help our societies and will open new avenues in developing solutions to future smart systems and technologies.
暂无评论