With the rapid development of the oil refining industry, safety problems caused by equipment corrosion have become increasingly important, making equipment corrosion management a key factor to ensure process safety. C...
详细信息
With the rapid development of the oil refining industry, safety problems caused by equipment corrosion have become increasingly important, making equipment corrosion management a key factor to ensure process safety. Corrosion diagnosis, as the first step of equipment corrosion management, is of great sign ificance in not only ensuring the proper corrosion supervision, but also realizing safety protection of equipment. This paper addresses the problems of incompleteness as well as the subjective factors of existing methods in equipment corrosion diagnosis. The proposed solution, based on data-driven corrosion diagnosis, suggests a more comprehensive view. Special focus in this paper is on evaluation and prediction of corrosion safety state, including the identification of corrosion mode and the prediction of corrosion type and degree. This paper brings together large amount of historical data of equipment corrosion detection and solves the problem of unbalanced original data by data wrangling and the application of Borderline-SMOTE algorithm. What's more, a prediction model that is based on Random Forest (RF) algorithm is constructed, aiming at equipment corrosion mechanism, type and degree. The results show that the model, aiming at critical mechanism identification, performs ideally after evaluation and the accuracy of the results amount to 86%. As for the classification and prediction of corrosion state, the model can be further optimized by Particle Swarm Optimization (PSO) algorithm to reach a better accuracy (92%), which verifies generalization effect compared with traditional prediction models. In addition, this solution improves the functionality and practicability of corrosion diagnosis, which is beneficial to the investigation of hidden dangers. It also can serve as an instruction for equipment safety management to ensure the stable operation for an enterprise. (C) 2021 Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.
Deep learning has achieved good performance in short-term traffic forecasting recently. However, the stochasticity and distribution imbalance are main characteristics to traffic flow, and these will bring the uncertai...
详细信息
Deep learning has achieved good performance in short-term traffic forecasting recently. However, the stochasticity and distribution imbalance are main characteristics to traffic flow, and these will bring the uncertainty and induce the network overfitting problem during deep learning. To deal with the problems, a new end-to-end hybrid deep learning network model, named M-B-LSTM, is proposed for short-term traffic flow forecasting in this paper. In the M-B-LSTM model, an online self-learning network is constructed as a data mapping layer to learn and equalize the traffic flow statistic distribution for reducing the effect of distribution imbalance and overfitting problem during network learning. Besides, the deep bidirectional long short-term memory network (DBLSTM) is introduced to reduce the uncertainty problem by forward and reverse contexts approximation process in the stochasticity reducing layer, and then the long short-term memory network (LSTM) is used to forecast the next traffic flow state in the forecasting layer. Furthermore, sufficient comparative experiments have been conducted and the results show the proposed model has better ability on solving uncertainty and overfitting problems than the state-of-art methods.
The distribution transformer is a critical component of the power system, and its stable operation directly affects system reliability. Addressing its fault diagnosis is essential for maintaining system stability. How...
详细信息
The imbalance between different types of DGA data in transformers makes power transformer fault diagnosis models tend to identify the tested samples as categories with a higher proportion in the training samples, whic...
详细信息
暂无评论