22 March 2019 in IEEE Transactions on Industrial Electronics
Recently, deep learning based representation learning methods have attracted increasing attention in machine fault diagnosis. However, few existing methods consider the geometry of data samples. In this paper, we propose a novel method to obtain representations that preserve the geometry of input data. More specifically, we formulate two cost functions to preserve the local and global geometries of input data respectively and another cost function to reconstruct the input data. Furthermore, to simplify the training process, we formulate a discrimination cost function based on the label information. By jointly optimizing all cost functions, the method can efficiently learn discriminative representations with the local and global geometry of input data preserved. Furthermore, the proposed method can obtain hierarchical representations without any additional tuning step. On two benchmark datasets, the proposed method demonstrates better fault classification performance and shorter training and test time. Therefore, it is an efficient tool to provide accurate information about machine conditions for making maintenance decision and saving costs.
1 May 2022 in Advanced Intelligent Systems
BABuvna Ayyagari-Sangamalli
Buvna Ayyagari-Sangamalli
+5
As the demands of big data applications and deep learning continue to rise, the industry is increasingly looking to artificial intelligence (AI) accelerators. Analog in‐memory computing (AiMC) with emerging nonvolatile devices enable good hardware solutions, due to its high energy efficiency in accelerating the multiply‐and‐accumulation (MAC) operation. Herein, an Applied Materials custom‐designed system‐on‐chip (SoC) targeting AI applications with analog in‐memory computing using resistive random‐access memory (ReRAM) as the compute element is demonstrated. The first silicon achieves high energy efficiency in MAC operations. This chip is implemented with LeNet‐1 neural network on ReRAM tiles and demonstrated by Modified National Institute of Standards and Technology (MNIST) classification with accuracy matching that predicted in the simulations. A simulation framework, AI Sim, is also developed to evaluate the system performance for large‐scale application and guide the bitcell development and design choices.
1 January 2022 in Separation and Purification Technology
1 December 2015 in Computers in Biology and Medicine
5 February 2020 in Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering
In high-speed airflow, the use of cavity and struts in combination can improve fuel distribution and flame-stabilization, but may weaken the ignition performance. Herein, the lean ignition characteristics of several cavity–strut flame holders in a tandem turbine-based combined cycles combustor are experimentally investigated with the flow fields by using particle image velocimetry and high-speed chemiluminescence imaging techniques. Additionally, the effects of the strut structure parameters on the lean ignition performance in the cavity are studied. Experimental results indicate that changes in structural parameters have the opposite effects on the ignition performance and the flame-propagation performance. Reducing the strut inclination angle has a contrary function with the decrease in the cavity–strut space, which also transforms the flame-stabilizing mechanism between strut-stabilizing and cavity-stabilizing, accompanied by the flame morphology behind strut changes from no-flame to intermittent-flame, and finally continuous-flame. The lean ignition limit changes with the structure parameters, mainly due to the inverse change in the mass exchange rate and cavity residence time. Compared with the single cavity, the proper cavity–strut combined structure has a wider lean ignition limit at high subsonic speeds due to the advantage of simultaneously increasing the mass exchange rate and cavity residence time.
1 February 2020 in Neural Networks