ویراساینس.
سند علمی

Data driven process monitoring based on neural networks and classification trees

Yifeng Zhou

چکیده

Data Driven Process Monitoring Based on Neural Networks and Classification Trees. (August 2004) Yifeng Zhou, B.S., Xian Jiao-Tong University, China; M.S., Research Institute of Petroleum Processing, China Chair of Advisory Committee: Dr. M. Sam Mannan Process monitoring in the chemical and other process industries has been of great practical importance. Early detection of faults is critical in avoiding product quality deterioration, equipment damage, and personal injury. The goal of this dissertation is to develop process monitoring schemes that can be applied to complex process systems. Neural networks have been a popular tool for modeling and pattern classification for monitoring of process systems. However, due to the prohibitive computational cost caused by high dimensionality and frequently changing operating conditions in batch processes, their applications have been difficult. The first part of this work tackles this problem by employing a polynomial-based data preprocessing step that greatly reduces the dimensionality of the neural network process model. The process measurements and manipulated variables go through a polynomial regression step and the polynomial coefficients, which are usually of far lower dimensionality than the original data, are used to build a neural network model to produce residuals for fault

اسناد مشابه

  • Process monitoring based on classification tree and discriminant analysis

    سند علمی۲۰۰۶Rel. Eng. & Sys. SafetyYifeng Zhou, Juergen Hahn, M. Sam Mannan

    To cope with the computational intensity associated with classification tree analysis and the multicolinearity in the process data, a newly developed process monitoring scheme integrating classification tree and Fisher Discriminant Analysis (FDA) is developed. FDA extracts the mo

  • Data Pre-processing for Neural Network-based Forecasting: Does It

    سند علمی۲۰۱۴REALLY MATTER

    This study aims to analyze the effects of data pre-processing on the forecasting performance of neural network models. We use three different Artificial Neural Networks techniques to predict tourist demand: multi-layer perceptron, radial basis function and Elman neural networks.

  • Data-Driven Processing in Sensor Networks

    سند علمی۲۰۰۷CIDRAdam Silberstein, Gregory Filpus, Kamesh Munagala, Jun Yang

    Wireless sensor networks are poised to enable continuous data collection on unprecedented scales, in terms of area location and size, and frequency. This is a great boon to fields such as ecological modeling. We are collaborating with researchers to build sophisticated temporal a

  • Data augmentation and deep neural network classification based on ship radiated noise

    مقاله‌ی دسترسی آزاد۲۰۲۳Frontiers in Marine Science['Zhuofan Xie', 'Renping Lin', 'Lingzhe Wang', 'Anmin Zhang', 'Jiaqing Lin', 'Tang Xiaoda', '']

    Introduction Various types of ships sail at sea, and identifying maritime ship through shipradiated noise is one the tasks ocean observation. The environment complex changeable, such rapid environmental changes underline difficulties obtaining a huge amount samples. Meanwhile, le

  • Industrial Application of Data-Driven Process Monitoring with an Automatic Selection Strategy for Modeling Data

    مقاله‌ی دسترسی آزاد۲۰۲۳Processes['Wei Sun', 'Zhuoteng Zhou', 'Fangyuan Ma', 'Jingde Wang', 'Cheng Ji', '']

    The increasing scale of industrial processes has significantly motivated the development data-driven fault detection and diagnosis techniques. selection representative fault-free modeling data from operation history is an important prerequisite to establishing a long-term effecti

  • An improved mixture of probabilistic PCA for nonlinear data-driven process monitoring

    سند علمی۲۰۱۷Jingxin Zhang, Hao Chen, Songhang Chen

    An improved mixture of probabilistic principal component analysis (PPCA) has been introduced for nonlinear datadriven process monitoring in this paper. To realize this purpose, the technique of a mixture of probabilistic principal component analysers is utilized to establish the